names
stringlengths 1
98
| readmes
stringlengths 8
608k
| topics
stringlengths 0
442
| labels
stringclasses 6
values |
|---|---|---|---|
text-generation-webui | text generation web ui a gradio web ui for large language models its goal is to become the automatic1111 stable diffusion webui https github com automatic1111 stable diffusion webui of text generation image1 https github com oobabooga screenshots raw main print instruct png image2 https github com oobabooga screenshots raw main print chat png image1 https github com oobabooga screenshots raw main print default png image2 https github com oobabooga screenshots raw main print parameters png features 3 interface modes default two columns notebook and chat multiple model backends transformers https github com huggingface transformers llama cpp https github com ggerganov llama cpp exllama https github com turboderp exllama exllamav2 https github com turboderp exllamav2 autogptq https github com panqiwei autogptq gptq for llama https github com qwopqwop200 gptq for llama ctransformers https github com marella ctransformers autoawq https github com casper hansen autoawq dropdown menu for quickly switching between different models lora load and unload loras on the fly train a new lora using qlora precise instruction templates for chat mode including llama 2 chat alpaca vicuna wizardlm stablelm and many others 4 bit 8 bit and cpu inference through the transformers library use llama cpp models with transformers samplers llamacpp hf loader multimodal pipelines including llava and minigpt 4 https github com oobabooga text generation webui tree main extensions multimodal extensions framework https github com oobabooga text generation webui wiki 07 e2 80 90 extensions custom chat characters https github com oobabooga text generation webui wiki 03 e2 80 90 parameters tab character very efficient text streaming markdown output with latex rendering to use for instance with galactica https github com paperswithcode galai api including endpoints for websocket streaming see the examples https github com oobabooga text generation webui blob main api examples documentation to learn how to use the various features check out the documentation https github com oobabooga text generation webui wiki installation one click installers 1 clone or download https github com oobabooga text generation webui archive refs heads main zip the repository 2 run the start linux sh start windows bat start macos sh or start wsl bat script depending on your os 3 select your gpu vendor when asked 4 have fun how it works the script creates a folder called installer files where it sets up a conda environment using miniconda the installation is self contained if you want to reinstall just delete installer files and run the start script again to launch the webui in the future after it is already installed run the same start script getting updates run update linux sh update windows bat update macos sh or update wsl bat running commands if you ever need to install something manually in the installer files environment you can launch an interactive shell using the cmd script cmd linux sh cmd windows bat cmd macos sh or cmd wsl bat defining command line flags to define persistent command line flags like listen or api edit the cmd flags txt file with a text editor and add them there flags can also be provided directly to the start scripts for instance start linux sh listen other info there is no need to run any of those scripts as admin root for additional instructions about amd setup wsl setup and nvcc installation consult the documentation https github com oobabooga text generation webui wiki the installer has been tested mostly on nvidia gpus if you can find a way to improve it for your amd intel arc mac metal gpu you are highly encouraged to submit a pr to this repository the main file to be edited is one click py for automated installation you can use the gpu choice use cuda118 launch after install and install extensions environment variables for instance gpu choice a use cuda118 false launch after install false install extensions false start linux sh manual installation using conda recommended if you have some experience with the command line 0 install conda https docs conda io en latest miniconda html on linux or wsl it can be automatically installed with these two commands source https educe ubc github io conda html curl sl https repo anaconda com miniconda miniconda3 latest linux x86 64 sh miniconda3 sh bash miniconda3 sh 1 create a new conda environment conda create n textgen python 3 11 conda activate textgen 2 install pytorch system gpu command linux wsl nvidia pip3 install torch torchvision torchaudio index url https download pytorch org whl cu121 linux wsl cpu only pip3 install torch torchvision torchaudio index url https download pytorch org whl cpu linux amd pip3 install torch torchvision torchaudio index url https download pytorch org whl rocm5 6 macos mps any pip3 install torch torchvision torchaudio windows nvidia pip3 install torch torchvision torchaudio index url https download pytorch org whl cu121 windows cpu only pip3 install torch torchvision torchaudio the up to date commands can be found here https pytorch org get started locally for nvidia you may also need to manually install the cuda runtime libraries conda install y c nvidia label cuda 12 1 0 cuda runtime 3 install the web ui git clone https github com oobabooga text generation webui cd text generation webui pip install r requirements file according to table below requirements file to use gpu cpu requirements file to use nvidia has avx2 requirements txt nvidia no avx2 requirements noavx2 txt amd has avx2 requirements amd txt amd no avx2 requirements amd noavx2 txt cpu only has avx2 requirements cpu only txt cpu only no avx2 requirements cpu only noavx2 txt apple intel requirements apple intel txt apple apple silicon requirements apple silicon txt amd gpu on windows 1 use requirements cpu only txt or requirements cpu only noavx2 txt in the command above 2 manually install llama cpp python using the appropriate command for your hardware installation from pypi https github com abetlen llama cpp python installation with hardware acceleration use the llama hipblas on toggle note the windows remarks https github com abetlen llama cpp python windows remarks 3 manually install autogptq installation https github com panqiwei autogptq install from source perform the from source installation there are no prebuilt rocm packages for windows 4 manually install exllama https github com turboderp exllama by simply cloning it into the repositories folder it will be automatically compiled at runtime after that sh cd text generation webui git clone https github com turboderp exllama repositories exllama older nvidia gpus 1 for kepler gpus and older you will need to install cuda 11 8 instead of 12 pip3 install torch torchvision torchaudio index url https download pytorch org whl cu118 conda install y c nvidia label cuda 11 8 0 cuda runtime 2 bitsandbytes 0 39 may not work in that case to use load in 8bit you may have to downgrade like this linux pip install bitsandbytes 0 38 1 windows pip install https github com jllllll bitsandbytes windows webui raw main bitsandbytes 0 38 1 py3 none any whl manual install the requirments txt above contain various precompiled wheels if you wish to compile things manually or if you need to because no suitable wheels are available for your hardware you can use requirements nowheels txt and then install your desired loaders manually alternative docker ln s docker dockerfile docker compose yml dockerignore cp docker env example env edit env and set torch cuda arch list based on your gpu model docker compose up build you need to have docker compose v2 17 or higher installed see this guide https github com oobabooga text generation webui wiki 09 e2 80 90 docker for instructions for additional docker files check out this repository https github com atinoda text generation webui docker updating the requirements from time to time the requirements txt changes to update use these commands conda activate textgen cd text generation webui pip install r requirements file that you ve used upgrade downloading models models should be placed in the text generation webui models folder they are usually downloaded from hugging face https huggingface co models pipeline tag text generation sort downloads transformers or gptq models are made of several files and must be placed in a subfolder example text generation webui models lmsys vicuna 33b v1 3 config json generation config json pytorch model 00001 of 00007 bin pytorch model 00002 of 00007 bin pytorch model 00003 of 00007 bin pytorch model 00004 of 00007 bin pytorch model 00005 of 00007 bin pytorch model 00006 of 00007 bin pytorch model 00007 of 00007 bin pytorch model bin index json special tokens map json tokenizer config json tokenizer model gguf models are a single file and should be placed directly into models example text generation webui models llama 2 13b chat q4 k m gguf in both cases you can use the model tab of the ui to download the model from hugging face automatically it is also possible to download via the command line with python download model py organization model use help to see all the options gpt 4chan details summary instructions summary gpt 4chan https huggingface co ykilcher gpt 4chan has been shut down from hugging face so you need to download it elsewhere you have two options torrent 16 bit https archive org details gpt4chan model float16 32 bit https archive org details gpt4chan model direct download 16 bit https theswissbay ch pdf notpdf gpt4chan model float16 32 bit https theswissbay ch pdf notpdf gpt4chan model the 32 bit version is only relevant if you intend to run the model in cpu mode otherwise you should use the 16 bit version after downloading the model follow these steps 1 place the files under models gpt4chan model float16 or models gpt4chan model 2 place gpt j 6b s config json file in that same folder config json https huggingface co eleutherai gpt j 6b raw main config json 3 download gpt j 6b s tokenizer files they will be automatically detected when you attempt to load gpt 4chan python download model py eleutherai gpt j 6b text only when you load this model in default or notebook modes the html tab will show the generated text in 4chan format image3 https github com oobabooga screenshots raw main gpt4chan png details starting the web ui conda activate textgen cd text generation webui python server py then browse to http localhost 7860 theme dark optionally you can use the following command line flags basic settings flag description h help show this help message and exit multi user multi user mode chat histories are not saved or automatically loaded warning this is likely not safe for sharing publicly character character the name of the character to load in chat mode by default model model name of the model to load by default lora lora lora the list of loras to load if you want to load more than one lora write the names separated by spaces model dir model dir path to directory with all the models lora dir lora dir path to directory with all the loras model menu show a model menu in the terminal when the web ui is first launched settings settings file load the default interface settings from this yaml file see settings template yaml for an example if you create a file called settings yaml this file will be loaded by default without the need to use the settings flag extensions extensions extensions the list of extensions to load if you want to load more than one extension write the names separated by spaces verbose print the prompts to the terminal chat buttons show buttons on the chat tab instead of a hover menu model loader flag description loader loader choose the model loader manually otherwise it will get autodetected valid options transformers exllama hf exllamav2 hf exllama exllamav2 autogptq gptq for llama llama cpp llamacpp hf ctransformers autoawq accelerate transformers flag description cpu use the cpu to generate text warning training on cpu is extremely slow auto devices automatically split the model across the available gpu s and cpu gpu memory gpu memory gpu memory maximum gpu memory in gib to be allocated per gpu example gpu memory 10 for a single gpu gpu memory 10 5 for two gpus you can also set values in mib like gpu memory 3500mib cpu memory cpu memory maximum cpu memory in gib to allocate for offloaded weights same as above disk if the model is too large for your gpu s and cpu combined send the remaining layers to the disk disk cache dir disk cache dir directory to save the disk cache to defaults to cache load in 8bit load the model with 8 bit precision using bitsandbytes bf16 load the model with bfloat16 precision requires nvidia ampere gpu no cache set use cache to false while generating text this reduces vram usage slightly but it comes at a performance cost xformers use xformer s memory efficient attention this is really old and probably doesn t do anything sdp attention use pytorch 2 0 s sdp attention same as above trust remote code set trust remote code true while loading the model necessary for some models use fast set use fast true while loading the tokenizer accelerate 4 bit requires minimum compute of 7 0 on windows at the moment flag description load in 4bit load the model with 4 bit precision using bitsandbytes use double quant use double quant for 4 bit compute dtype compute dtype compute dtype for 4 bit valid options bfloat16 float16 float32 quant type quant type quant type for 4 bit valid options nf4 fp4 llama cpp flag description n ctx n ctx size of the prompt context threads number of threads to use threads batch threads batch number of threads to use for batches prompt processing no mul mat q disable the mulmat kernels n batch maximum number of prompt tokens to batch together when calling llama eval no mmap prevent mmap from being used mlock force the system to keep the model in ram n gpu layers n gpu layers number of layers to offload to the gpu tensor split tensor split split the model across multiple gpus comma separated list of proportions example 18 17 llama cpp seed seed seed for llama cpp models default is 0 random numa activate numa task allocation for llama cpp cache capacity cache capacity maximum cache capacity llama cpp python examples 2000mib 2gib when provided without units bytes will be assumed exllama flag description gpu split comma separated list of vram in gb to use per gpu device for model layers example 20 7 7 max seq len max seq len maximum sequence length cfg cache exllama hf create an additional cache for cfg negative prompts necessary to use cfg with that loader but not necessary for cfg with base exllama autogptq flag description triton use triton no inject fused attention disable the use of fused attention which will use less vram at the cost of slower inference no inject fused mlp triton mode only disable the use of fused mlp which will use less vram at the cost of slower inference no use cuda fp16 this can make models faster on some systems desc act for models that don t have a quantize config json this parameter is used to define whether to set desc act or not in basequantizeconfig disable exllama disable exllama kernel which can improve inference speed on some systems gptq for llama flag description wbits wbits load a pre quantized model with specified precision in bits 2 3 4 and 8 are supported model type model type model type of pre quantized model currently llama opt and gpt j are supported groupsize groupsize group size pre layer pre layer pre layer the number of layers to allocate to the gpu setting this parameter enables cpu offloading for 4 bit models for multi gpu write the numbers separated by spaces eg pre layer 30 60 checkpoint checkpoint the path to the quantized checkpoint file if not specified it will be automatically detected monkey patch apply the monkey patch for using loras with quantized models ctransformers flag description model type model type model type of pre quantized model currently gpt2 gptj gptneox falcon llama mpt starcoder gptbigcode dollyv2 and replit are supported deepspeed flag description deepspeed enable the use of deepspeed zero 3 for inference via the transformers integration nvme offload dir nvme offload dir deepspeed directory to use for zero 3 nvme offloading local rank local rank deepspeed optional argument for distributed setups rwkv flag description rwkv strategy rwkv strategy rwkv the strategy to use while loading the model examples cpu fp32 cuda fp16 cuda fp16i8 rwkv cuda on rwkv compile the cuda kernel for better performance rope for llama cpp exllama exllamav2 and transformers flag description alpha value alpha value positional embeddings alpha factor for ntk rope scaling use either this or compress pos emb not both rope freq base rope freq base if greater than 0 will be used instead of alpha value those two are related by rope freq base 10000 alpha value 64 63 compress pos emb compress pos emb positional embeddings compression factor should be set to context length model s original context length equal to 1 rope freq scale gradio flag description listen make the web ui reachable from your local network listen port listen port the listening port that the server will use listen host listen host the hostname that the server will use share create a public url this is useful for running the web ui on google colab or similar auto launch open the web ui in the default browser upon launch gradio auth user pwd set gradio authentication password in the format username password multiple credentials can also be supplied with u1 p1 u2 p2 u3 p3 gradio auth path gradio auth path set the gradio authentication file path the file should contain one or more user password pairs in the same format as above ssl keyfile ssl keyfile the path to the ssl certificate key file ssl certfile ssl certfile the path to the ssl certificate cert file api flag description api enable the api extension public api create a public url for the api using cloudfare public api id public api id tunnel id for named cloudflare tunnel use together with public api option api blocking port blocking port the listening port for the blocking api api streaming port streaming port the listening port for the streaming api multimodal flag description multimodal pipeline pipeline the multimodal pipeline to use examples llava 7b llava 13b google colab notebook https colab research google com github oobabooga text generation webui blob main colab textgen gpu ipynb contributing if you would like to contribute to the project check out the contributing guidelines https github com oobabooga text generation webui wiki contributing guidelines community subreddit https www reddit com r oobabooga discord https discord gg jwzcf2dpqn acknowledgment in august 2023 andreessen horowitz https a16z com a16z provided a generous grant to encourage and support my independent work on this project i am extremely grateful for their trust and recognition which will allow me to dedicate more time towards realizing the full potential of text generation webui | ai |
|
milton_relay | a name readme top a project logo br div align center a href https github com kooperlol milton relay img src https raw githubusercontent com kooperlol milton relay master assets miltonrelay logo png alt logo width 110 height 80 a h3 align center milton relay h3 p align center a project for fbla mobile app development 2022 2023 p div about the project about the project milton relay is a mobile application for my school to help keep parents and the community up to date the app includes upcoming events important information such as the school calendar and activities schedule a way for teachers and students to share photos and a way for parents to notify the school of student absences in addition i added a laude point calculator recommended by the school administration in the program there is a admin student teacher and parent interface each with different features program awards 1 wisconsin state br 4 georgia nationals requirements met the program meets the requirements stated on the fbla application development rubric https www fbla pbl org media mobile application development fbla rating sheet 1 pdf x packaged with complete file readme and instructions the readme contains instructions and relevant information the program is packaged so that it can easily be cloned and ran on another machine x application functionality the application is compatible with both ios and android in addition it can be resized to display on phones and tablets x documentation and copyright compliance the application is licensed under mit and all resources used are cited below and copyright free x application addresses the topic the application addresses the topic fully by including a news feed photo sharing student absences a calendar and a feature recommend by my school administration x planning process tangible documents will be provided to show the planning process this includes some flowcharts google documents and figma blueprints x navigation the app navigation is simplistic and easy to use with there being a bottom navigation bar and header containing intuitive ui x code the code contains comments and all code is error free during compilation if runtime errors occur they can be reported through the bug report system x icons and graphics the milton relay logo is integrated into the app s header which is persistent throughout the app s ui in addition it relates to the app as it has our school mascot within a chat box which shows that it is a communication app for our school x social media the school s facebook is linked on the news page so students can easily access school district feed on the media sharing tab there is an option to share your post directly with instagram or twitter x bugs the application does not have any known bugs however if a bug is stumbled upon a user can easily report the bug through the app s bug report system built with technology description flutter flutter https flutter dev a framework that can compile to multiple operating systems from just one coding language firebase firebase https firebase google com a backend database used for authentication file storage and document storage dependencies dependencies table calendar https pub dev packages table calendar image picker https pub dev packages image picker flutter spinkit https pub dev packages flutter spinkit responsive sizer https pub dev packages responsive sizer getwidget https pub dev packages getwidget social share https pub dev packages social share add 2 calendar https pub dev packages add 2 calendar dotenv https pub dev packages flutter dotenv checkbox grouped https pub dev packages checkbox grouped intl https pub dev packages intl loader overlay https pub dev packages loader overlay multiselect https pub dev packages multiselect uuid https pub dev packages uuid webview flutter https pub dev packages webview flutter gorouter https pub dev packages go router flutter svg https pub dev packages flutter svg dots indicator https pub dev packages dots indicator readmore https pub dev packages readmore url launcher https pub dev packages url launcher path https pub dev packages path http https pub dev packages http path provider https pub dev packages path provider external resources external resources undraw https undraw co tagbox https taggbox com pexels https www pexels com ux wing https uxwing com opensans https fonts google com specimen open sans best readme template https github com othneildrew best readme template github image shields https github com badges shields compatibility compatibility ios ios br android android getting started getting started to get a local copy up and running follow these simple steps prerequisites install the following before cloning the project flutter https docs flutter dev get started install an emulator https www geeksforgeeks org how to run a flutter app on android emulator installation clone the repository and compile the code in an ide such as android studio xcode or visual studio code go to firebase and create an account after that create a project that supports ios and or android and follow the given steps add the following modules to the project authentication firestore and storage in authentication create an admin account with the email admin school domain com and make a secure password in firestore database create a users posts absences issues and events collection in storage create an avatars events issues and posts folder then launch the application and sign in as an administrator navigate to the users tab and at the top click the add user button from there add all of the students teachers and parents to the application instructions https github com kooperlol milton relay blob master documentation instructions pdf planning process https github com kooperlol milton relay blob master documentation planning process pdf license license distributed under the mit license see license txt for more information contact contact kooper propp kooperjack8 gmail com br project link https github com kooperlol milton relay https github com kooperlol milton relay markdown links images license shield https img shields io github license othneildrew best readme template svg style for the badge flutter https img shields io badge flutter 2302569b svg style for the badge logo flutter logocolor white firebase https img shields io badge firebase 039be5 style for the badge logo firebase logocolor white ios https img shields io badge ios 000000 style for the badge logo ios logocolor white android https img shields io badge android 3ddc84 style for the badge logo android logocolor white | dart fbla fbla-2023 fbla-mobile-application-development flutter school-management-system | front_end |
NLP-Fake-News-Challenge | fake news challenge the idea of fake news is often referred to as click bait in social trends and is defined as a made up story with an intention to deceive geared towards getting clicks tavernise 2016 some news articles have titles which grab a reader s interest yet the author only emphasizes a specific part of the article in the title if the article itself does not focus on or give much truth to what the title had written the news may be misleading the goal of this project is to use natural language processing techniques to automate stance detection since it is not practical for humans to fact check every piece of information produced by the media stance detection is a method used to determine the quality of a news article by taking into consideration what other organisations write about the same headline a body of text is claimed to agree disagree discuss or be unrelated to a headline fake news challenge 2016 stance detection is the method that will be used to determine the quality of a news source from the fakechallenge org http fakenewschallenge org a dataset will be provided which consists of a headline and a body of text this body of text may be from a different article allowing bodies of text from different articles allows this system to take into account what the other organisations are saying about he same headline the output of the system will be the stance of the body of text related to the title as shown in the fake news challenge fake news source the system will support will support the following stance types agrees disagrees discusses unrelated with this system for a set of news headlines statistics can be gathered with respect to the stances with these statistics a user can come to their own conclusion of whether a new organisation has reputable news sources to achieve these stances this system will train on the data supplied by the fake news challenge this data will provide the stance along with the headline and body to allow the system to learn which word combinations lead to which stance for testing data will be provided without the stances to expand upon the baseline this project will consider stemming words removing stop words and smoothing developer commands to generate the features br python feature generation py to train and get analysis br python model py sources this project was inspired by the fake news challenge fnc fnc baseline repo https github com fakenewschallenge fnc 1 baseline br fakechallenge org http fakenewschallenge org br fnc 1 repo https github com fakenewschallenge fnc 1 | ai |
|
CVPR-2019-Paper-Statistics | cvpr paper statistics statistics and visualization of acceptance rate main keyword of cvpr 2019 accepted papers for the main computer vision conference cvpr 2019 http cvpr2019 thecvf com inspired by iclr2019 openreviewdata https github com shaohua0116 iclr2019 openreviewdata p align center img width 600 src 2019 cvpr keyword cloud title png p cvpr 2019 acceptance rate 2015 2019 the total number of papers is increasing every year and this year has increased significantly the acceptance rate decreased from 30 to 25 p align center img width 500 src 2019 cvpr cvpr acceptance rate png p cvpr 2019 simple paper review 20 papers slide https www slideshare net hoseonglee6 2019 cvpr paperoverview cvpr paper keywords statistics accepted paper list https github com hoya012 cvpr paper statistics blob master 2019 cvpr cvpr 2019 poster csv most of the top keywords were maintained image detection 3d object video segmentation adversarial recognition visual graph cloud representation are about twice as frequent graph 15 45 representation 25 48 cloud 16 35 p align center img width 1000 src 2019 cvpr top keywords 2019 2018 png p analysis and visualization code jupyter notebook the above data can be obtained from a simple jupyter notebook script i wrote two versions of the code cvpr paper statistics using csv ipynb https github com hoya012 cvpr paper statistics blob master cvpr paper statistics using csv ipynb use csv data format cvpr paper statistics using chrome ipynb https github com hoya012 cvpr paper statistics blob master cvpr paper statistics using chrome ipynb use website data format prerequisites python3 5 selenium https selenium python readthedocs io wordcloud https pypi org project wordcloud matplotlib https matplotlib org or i highly recommend to use google colab https colab research google com just download jupyter notebook and move to your google drive and open with colaboratory | cvpr cvpr2019 paper statistics paper-analysis | ai |
nlp | natural language processing license mit https img shields io badge license mit yellow svg https opensource org licenses mit godoc https godoc org github com james bowman nlp status svg https godoc org github com james bowman nlp build status https travis ci org james bowman nlp svg branch master https travis ci org james bowman nlp go report card https goreportcard com badge github com james bowman nlp https goreportcard com report github com james bowman nlp codecov https codecov io gh james bowman nlp branch master graph badge svg https codecov io gh james bowman nlp mentioned in awesome go https awesome re mentioned badge flat svg https github com avelino awesome go sourcegraph https sourcegraph com github com james bowman nlp badge svg https sourcegraph com github com james bowman nlp badge img src https github com james bowman nlp raw master gophers 008 crop png alt nlp align left implementations of selected machine learning algorithms for natural language processing in golang the primary focus for the package is the statistical semantics of plain text documents supporting semantic analysis and retrieval of semantically similar documents built upon the gonum https www gonum org package for linear algebra and scientific computing with some inspiration taken from python s scikit learn http scikit learn org stable and gensim https radimrehurek com gensim check out the companion blog post http www jamesbowman me post semantic analysis of webpages with machine learning in go or the go documentation page https godoc org github com james bowman nlp for full usage and examples br clear all features lsa latent semantic analysis aka latent semantic indexing lsi lsa implementation using truncated svd singular value decomposition https en wikipedia org wiki singular value decomposition for dimensionality reduction fast comparison and retrieval of semantically similar documents using simhash https en wikipedia org wiki simhash random hyperplanes sign random projection https en wikipedia org wiki locality sensitive hashing random projection algorithm with multi index and forest schemes for lsh locality sensitive hashing https en wikipedia org wiki locality sensitive hashing to support fast approximate cosine similarity angular distance comparisons and approximate nearest neighbour search using significantly less memory and processing time random indexing ri https en wikipedia org wiki random indexing and reflective random indexing rri which extends ri to support indirect inference for scalable latent semantic analysis lsa lsa over large web scale corpora latent dirichlet allocation lda https en wikipedia org wiki latent dirichlet allocation using a parallelised implementation of the fast scvb0 stochastic collapsed variational bayesian inference scvb0 algorithm for unsupervised topic extraction pca principal component analysis https en wikipedia org wiki principal component analysis tf idf https en wikipedia org wiki tf e2 80 93idf weighting to account for frequently occuring words sparse matrix http github com james bowman sparse implementations used for more efficient memory usage and processing over large document corpora stop word removal to remove frequently occuring english words e g the and feature hashing https en wikipedia org wiki feature hashing the hashing trick implementation using murmurhash3 http github com spaolacci murmur3 for reduced memory requirements and reduced reliance on training data similarity distance measures to calculate the similarity distance between feature vectors planned expanded persistence support stemming to treat words with common root as the same e g go and going clustering algorithms e g heirachical k means etc classification algorithms e g svm knn random forest etc references 1 rosario barbara latent semantic indexing an overview infosys 240 spring 2000 http people ischool berkeley edu rosario projects lsi pdf 1 latent semantic analysis a scholarpedia article on lsa written by tom landauer one of the creators of lsa http www scholarpedia org article latent semantic analysis 1 thomo alex latent semantic analysis tutorial http webhome cs uvic ca thomo svd pdf 1 latent semantic indexing standford nlp course http nlp stanford edu ir book html htmledition latent semantic indexing 1 html 1 charikar moses s similarity estimation techniques from rounding algorithms in proceedings of the thiry fourth annual acm symposium on theory of computing stoc 02 2002 p 380 https www cs princeton edu courses archive spr04 cos598b bib charikarestim pdf 1 m bawa t condie and p ganesan lsh forest self tuning indexes for similarity search proc 14th int conf world wide web www 05 p 651 2005 http dl acm org citation cfm id 1060745 1060840 1 a gionis p indyk and r motwani similarity search in high dimensions via hashing vldb 99 proc 25th int conf very large data bases vol 99 no 1 pp 518 529 1999 http www cs princeton edu courses archive spring13 cos598c gionis pdf 5cnhttp portal acm org citation cfm id 671516 1 kanerva pentti kristoferson jan and holst anders 2000 random indexing of text samples for latent semantic analysis http citeseerx ist psu edu viewdoc download doi 10 1 1 4 6523 rep rep1 type pdf 1 rangan venkat discovery of related terms in a corpus using reflective random indexing https www umiacs umd edu oard desi4 papers rangan pdf 1 vasuki vidya and cohen trevor reflective random indexing for semi automatic indexing of the biomedical literature https ac els cdn com s1532046410000481 1 s2 0 s1532046410000481 main pdf tid f31f92e8 028a 11e8 8c31 00000aab0f6c acdnat 1516965824 e24a804445fff1744281ca6f5898a3a4 1 qasemizadeh behrang and handschuh siegfried random indexing explained with high probability http pars ie publications papers pre prints random indexing dr explained pdf 1 foulds james boyles levi dubois christopher smyth padhraic welling max 2013 stochastic collapsed variational bayesian inference for latent dirichlet allocation scvb0 1 geva shlomo de vries christopher m 2011 topsig topology preserving document signatures https eprints qut edu au 43451 4 43451 pdf lsa https en wikipedia org wiki latent semantic analysis scvb0 https arxiv org pdf 1305 2452 | go golang natural-language-processing nlp lsa latent-semantic-analysis machine-learning svd singular-value-decomposition tf-idf feature-hash locality-sensitive-hashing lsh random-projections simhash latent-semantic-indexing lsi random-indexing latent-dirichlet-allocation lda | ai |
udagram | udacity cloud engineering nanodegree project 2 udagram github repository https github com prashidi udagram local deployment 1 npm i 2 npm run dev 3 eb init 4 modify the elasticbeanstalk config yml file to include deploy artifact www archive zip 5 npm run build 6 eb create 7 eb deploy eb endpoint dev http udagram rashi dev us east 1 elasticbeanstalk com example http udagram rashi dev us east 1 elasticbeanstalk com filteredimage image url https images pexels com photos 45201 kitty cat kitten pet 45201 jpeg screenshots please check in the route directory deploement screenshots | cloud |
|
framework | the nx framework home page http nx framework com docs http nx framework com docs nx is a modular front end framework built with es6 and web components the building blocks of nx are the core the middlewares the components and the utilities these are all hosted in separate github repos and npm packages the nx core is a tiny library responsible for one thing only it allows you to create dumb components and to augment them with middlewares a component executes its middlewares when it is attached to the dom and it gains all the extra functionalities from them nx comes with some core middlewares out of the box which you can find listed below text interpolation interpolate values from the code into the view dynamically or one time includes optional filters dynamic and custom attributes use one time or dynamically evaluated native attributes or define some custom ones event handling add inline event handlers to listen on any event includes optional rate limiters visual flow use conditional blocks and loops inside the html view data binding one way one time or two way data binding on any event and with no edge cases rendering modularize your html and css code by moving them into separate files for each component routing simple but powerful routing with automatic parameter synchronization and router events metadata and analytics handle your spa s metadata and analytics declaratively with ease dynamic styling simplify styling by passing objects to the style and class attributes animations create powerful animations by using only a few html attributes some other low level middlewares mentioned in the docs anything else you define with the simple function middleware elem state next syntax these can be combined to create components with the desired functionality alternatively ready made core components can be extended and used to avoid boilerplate code resources home page http nx framework com docs http nx framework com docs intro app https github com nx js intro example todomvc https github com nx js todomvc example hacker news clone https github com nx js hackernews example blog http nx framework com blog public article series about writing nx https blog risingstack com writing a javascript framework project structuring installation you can get nx from npm with the npm install nx js framework command see the installation page http nx framework com install for other options local development you can bundle the framework locally with the npm run build command and minify it with the npm run minify command the bundled and minified files are placed in the lib folder contributing a list of contributors contributors md nx is very modular and every module is hosted in its own github repository please open the issues and prs in the relevant repositories for example if you have a feature request for routing open a new issue in the route middleware https github com nx js route middleware repo sponsored by a href https trace risingstack com img src http nx framework com images trace colored svg width 200 a | framework javascript frontend middlewares webcomponents es6 | front_end |
Hyper | h1 align center br img src https github com geeteshk hyper blob master art logo png raw true alt hyper logo title hyper logo br h1 p align center a href https travis ci org geeteshk hyper img src https travis ci org geeteshk hyper svg branch master a a href https github com geeteshk hyper blob master license img src https img shields io badge license apache 202 0 blue svg a a href https github com ellerbrock open source badges img src https badges frapsoft com os v3 open source png v 103 a a href https github com kotlinby awesome kotlin img src https kotlin link awesome kotlin svg a a href https codeclimate com github geeteshk hyper maintainability img src https api codeclimate com v1 badges 67cae6198e8414208053 maintainability a p p align center strong hyper strong is a powerful open source web development ide for android p h1 align center br img src https github com geeteshk hyper blob master art left png raw true width 427 height 768 img src https github com geeteshk hyper blob master art middle png raw true width 427 height 768 br h1 | hyper android web ide html css js editor http https git apps | front_end |
ripgrep.el | ripgrep el license gpl 2 badge license license coverage status https coveralls io repos nlamirault ripgrep el badge png branch master https coveralls io r nlamirault ripgrep el branch master master melpa stable https stable melpa org packages ripgrep badge svg https stable melpa org ripgrep circle ci https circleci com gh nlamirault ripgrep el tree master svg style svg https circleci com gh nlamirault ripgrep el tree master develop melpa status https melpa org packages ripgrep badge svg https melpa org ripgrep circle ci https circleci com gh nlamirault ripgrep el tree develop svg style svg https circleci com gh nlamirault ripgrep el tree develop ripgrep el allows you to search using ripgrep from inside emacs installation the recommended way to install ripgrep is via melpa m x package install ripgrep or cask depends on ripgrep there is also projectile ripgrep https melpa org projectile ripgrep if you want to use it using projectile https github com bbatsov projectile usage kbd m x ripgrep regexp kbd or kbd m x projectile ripgrep kbd development cask ripgrep el use cask for dependencies management install it and retrieve dependencies curl fsskl https raw github com cask cask master go python export path home cask bin path cask testing launch unit tests from shell make clean test using overseer keybinding description kbd c c t kbd launch unit tests from buffer kbd c c b kbd launch unit tests kbd c c g kbd launch unit tests with tag find regexp tips if you want to launch a single unit test add a specify tag lisp ert deftest test foobar tags current and launch it using kbd c c g kbd and specify tag current support contribute see here contributing md changelog a changelog is available here changelog md license see license license contact nicolas lamirault nicolas lamirault gmail com ripgrep el https github com nlamirault ripgrep el badge license https img shields io badge license gpl 2 green svg style flat license https github com nlamirault ripgrep el blob master license gnu emacs https www gnu org software emacs melpa https melpa org cask http cask github io issue tracker https github com nlamirault ripgrep el issues overseer https github com tonini overseer el ripgrep https github com burntsushi ripgrep | ripgrep emacs | front_end |
commercial-web-catalog-django | commercial web catalog django web based solution aims to present products as a catalog for commercial purposes harmonized by dynamic user interfence and easy use database engineering developer contact back end br muhammet c neyt topba br 90 530 035 46 85 br front end br esat sami topba br esatopbas gmail com br 90 530 035 46 86 br feel free to call | server |
|
aws-iot-device-client | aws iot device client notice running the aws iot device client will incur usage of aws iot services and is likely to incur charges on your aws account please refer the pricing pages for aws iot core https aws amazon com iot core pricing aws iot device management https aws amazon com iot device management pricing and aws iot device defender https aws amazon com iot device defender pricing for more details jump to introduction introduction installation installation setup configuration setup and configuration jobs feature source jobs readme md fleet provisioning feature source fleetprovisioning readme md device defender feature source devicedefender readme md secure tunneling feature source tunneling readme md named shadow feature source shadow readme md sample shadow feature source shadow sample shadow config shadow feature source shadow config shadow sensor publish feature source sensor publish readme md provisioning with secure elements feature source secure element readme md logging source logging readme md http proxy docs http proxy md samples source samples mqtt pub sub sample feature source samples pubsub readme md doxygen documentation docs readme md additional resources additional resources security security license license introduction sections current capabilities current capabilities list of supported platforms list of supported platforms back to the top aws iot device client the aws iot device client is free open source modular software written in c that you can compile and install on your embedded linux based iot devices to access aws iot core https aws amazon com iot core aws iot device management https aws amazon com iot device management and aws iot device defender https aws amazon com iot device defender features by default it serves as a reference implementation for your iot devices to work with aws iot services with operational best practices baked in using it is the easiest way to create a proof of concept poc for your iot project what s more since it is open source you can modify it to fit your business needs or optimize it when you wish to scale up from a poc to production current capabilities the modular iot device client consists of a base client and discrete client side features that support the following the base client handles mqtt connectivity with aws iot core it enables your iot device to automatically connect and make subscriptions to feature relevant mqtt topics it also provides a logging api for device side logs the client side jobs feature enables you to execute remote actions on your device when you use the jobs feature https aws amazon com iot device management features remotely manage connected devices of the aws iot device management service it provides support for a few remote actions by default and extensibility for custom actions you can use custom actions to remotely control the state of your iot devices the client side secure tunneling feature enables secure privileged access to your iot device when you use the secure tunneling feature https aws amazon com iot device management features secure tunneling in the aws iot device management service the client side device defender feature enables you to collect standard device side metrics https docs aws amazon com iot latest developerguide detect device side metrics html when you use the rules detect feature https docs aws amazon com iot latest developerguide detect device side metrics html in the aws iot device defender service the client side fleet provisioning feature enables you to replace provisional credentials with device specific ones when you onboard a fleet of devices using the fleet provisioning capability https docs aws amazon com iot latest developerguide provision wo cert html of aws iot core it creates a device specific certificate and private key and registers the device on aws iot core the client side named shadows feature enables you to control your iot device using aws iot named shadows https docs aws amazon com iot latest developerguide iot device shadows html shadows can store your device s state information and make it available to your device aws iot services your custom apps and other aws services whether the device is online and connected to aws iot or not list of supported platforms the aws iot device client is currently compatible with x86 64 aarch64 armv7l mips32 ppc64 and ppc64le architectures and common linux software environments debian ubuntu and rhel installation sections minimum requirements minimum requirements building from source building from source running the tests running the tests advanced compilation docs compilation md back to the top aws iot device client minimum requirements c 11 or higher cmake https cmake org 3 10 openssl 1 1 1 aws iot device sdk cpp v2 https github com aws aws iot device sdk cpp v2 commit hash located in cmakelists txt awssdk note the tls stack and the version of the sdk mentioned above is what our ci uses you could potentially use a different tls stack for example we just don t actively test or support this docker the aws iot device client currently provides several docker images on various platforms and linux distributions to build a docker image from the repository locally simply run the docker build sh docker build sh script with your preferred os ubuntu amazonlinux ubi8 e g docker build sh ubuntu if no os is passed the build will default to ubuntu 18 04 for a minimum sized fully built aws iot device client docker image simply pull your preferred architecture os combination from our repository here https gallery ecr aws aws iot device client aws iot device client docker files base images github docker images base images multi stage dockerfiles which will build dependencies only target base or build the device client from your current directory target deploy dockerfile github docker images dockerfile takes two build args os ubuntu amazonlinux ubi8 and base image image uri build target deploy will build device client from your current directory using the provided base image build target minimum size will build a minimum sized docker image with the device client binary using the base image building from source to use the aws iot device client you ll need to compile an executable using the source code provided by this repository below you ll find instructions for how to build the aws iot device client for your target machine quick start the following commands should work for most users when you plan to run the aws iot device client on the same machine that you re performing the compilation on building git clone https github com awslabs aws iot device client cd aws iot device client mkdir build cd build cmake cmake build target aws iot device client setup cd setup sh at this point you ll need to respond to prompts for information including paths to your thing certs run the aws iot device client aws iot device client this command runs the executable running the tests cmake cmake build target test aws iot device client build test test aws iot device client advanced compilation advanced compilation docs compilation md setup and configuration setting up the device client docs setup md configuring the aws iot device client docs config md file and directory permission requirements docs permissions md environment variables docs env md version docs version md http proxy docs http proxy md aws iot features jobs feature readme source jobs readme md fleet provisioning feature readme source fleetprovisioning readme md device defender feature readme source devicedefender readme md secure tunneling feature readme source tunneling readme md named shadow feature readme source shadow readme md sensor publish feature source sensor publish readme md provisioning with secure elements feature source secure element readme md aws iot device client samples mqtt pub sub sample feature source samples pubsub readme md logging logging readme source logging readme md doxygen documentation doxygen documentation readme docs readme md additional resources this section provides links to additional aws iot resources that may help you use and modify the aws iot device client api documentation generated by doxygen https awslabs github io aws iot device client annotated html related sdks samples and documentation https docs aws amazon com iot latest developerguide iot sdks html iot device sdks aws iot device sdk for c v2 https github com aws aws iot device sdk cpp v2 security see contributing contributing md security issue notifications for more information license this project is licensed under the apache 2 0 license back to the top aws iot device client | server |
|
designPattern | design pattern without oop abstract data type state machine implementation of a state machine that uses abstract data type in c c main cpp contains the client code of the state machine context abstractdatatype cpp demonstration of an incomplete data type that hides its implementation to the user state cpp contains the interface to the states and a default implementation of the states in case that a concrete state is not implemented in the statex cpp statex cpp contains the implementation of the available states | os |
|
FEL-B0B36PJV-SmartOrchestra | spustiteln soubor naleznete v adres i smartorchestra 1 0 stable v adres i db naleznete instala n skripty k datab zi zbyl adres e jsou struktura java projektu v mavenu | server |
|
information-technology-storage-control | div align center h1 projeto itsc h1 hr div div class sumario h3 sum rio h3 h6 objetivo h6 div class prefacio objetivo ul li objetivo li ul div h6 download e instala o h6 div class system requierements ul li instala o do sistema li li depend ncias li ul div h6 diagramas h6 div class diagramas ul li diagrama de arquitetura aplica o li li diagrama banco de dados li li diagrama back end li li diagrama front end li ul div h6 tecnologias de desenvolvimento h6 div class tecnologias e desenvolvimento ul li linguagem de programa o li li banco de dados li li arquitetura de desenvolvimento li li bibliotecas li ul div h6 desenvolvimento back end h6 div class back end ul li comunica o com banco de dados li li servi os li ul div h6 desenvolvimento interface grafica h6 div class front end ul li modelo de interface li li requisito de campos li li conex o de servi os li li implementa o de responsividade li ul div h6 banco de dados h6 div class my sql ul li informa es sobre o banco de dados li li modelagem da base li ul div h6 conclus o h6 div class conclusao ul li conclus o do projeto li ul div div div class sumario objetivo h3 objetivo h3 div | clean-code java mysql ports-and-adapters microservices sql swing | server |
peddler-pos | important notice this project is deprecated and will be ported to react native in the near future i am retaining this for educational purposes visit my site https flickos net blog for updates peddler pos mobile point of sale alt www img sales200 png sales alt www img sales keypad200 png sales keypad alt www img sales order200 png sales keypad alt www img settings200 png settings alt www img payments200 png settings alt www img checkout200 png settings overview offline first point of sale designed for mobile phones and tablets features 1 capture daily sales 2 view daily or date range sales report 3 backup sales to cloud 4 print sales to mobile thermal printer how test open build folder and install android debug apk to your phone or tablet how to build 1 clone this repository git clone https github com dvbondoy peddler pos git 2 change directory cd peddler pos 3 install ionic http ionicframework com docs guide installation html 4 build ionic run platform android ios goals 1 import products from csv file 2 export sales to csv file 3 monitor product inventory 4 role based login frameworks and libraries used 1 ionic framework 2 angularjs 3 pouchdb 4 some cordova plugins thanks to our contributors dgonz and mgonz | pos mobile-app ionic android android-app cordova angularjs | front_end |
sql_challenge | sql challenge | server |
|
blb | blb blb is a distributed object storage system designed for use on bare metal with spinning disks in cluster computing environments it s implemented in go the developer facing api is a client library also implemented in go that exposes objects with an interface similar to go files io readwriteseeker design philosophy blb was designed with the following ideals in mind in roughly this priority simplicity of architecture and implementation scalability ease of operation and administration optimized for large write rarely objects stored on spinning disks on commodity hardware architecture overview blb borrows many ideas from other storage systems most prominently google s gfs and colossus and microsoft s fds there are also some similarities to dropbox s magic pocket as in similar systems blobs are divided into fixed size tracts of 8mb tracts are spread across storage nodes in the cluster each storage node runs a tractserver that manages the storage on that node and exposes it to the network locations of tracts are stored in metadata servers called curators locations are stored explicitly not based on consistent hashing or a similar scheme this allows for the most control over data placement and movement curators store their metadata in an embedded database bolt db and use the raft protocol to guarantee consistency of updates across replicas objects also called blobs are identified with a fixed length numeric id currently 64 bits but will probably move to 128 objects are assigned to curators by a mapping from the upper bits of their id called the partition the partition to curator mapping is stored in another set of metadata servers called masters the masters also use raft to keep that mapping consistent currently partitions cannot be migrated from one curator to another this basic design is expected to scale to very large clusters just by adding more curators although the implementation certainly has various bottlenecks that will need to be addressed before that point to manipulate an object the client library talks with the masters curators and tractservers some metadata can be cached to reduce the number of round trips required to complete an operation storage tractservers store tracts as files in a regular filesystem on local disks we ve used ext4 future plans include raw disk storage bypassing the filesystem with optional support for host managed smr the tractserver is designed to have low memory and cpu requirements so it can easily coexist with other services in a converged storage configuration in our environment we observed it using 50 60mb per 4tb disk under moderate load curator and master metadata is stored in a local filesystem as well in bolt db files logs and db snapshots and should be on ssds for good performance durability blb supports two schemes for ensuring durability plain replication and reed solomon erasure coding all objects are created with replicated storage and can be optionally transitioned to erasure coded storage after which they cannot be written to anymore future plans may allow transitioning back to replicated storage when writing is requested the replication factor may be controlled by clients for rs erasure coding clients choose from one of several pre configured sets of parameters all data on disk is written with embedded crc32 checksums to detect corruption and errors in storage devices when full or partial disk failures are detected blb re replicates affected data on new disks in the cluster tractservers slowly scrub all their data to proactively detect failures consistency the main consistency guarantee provided is that after a successful write to a range of an object all reads from that range will return the data that was written if a write returns a failure future reads of that range may return anything though other ranges of the object are unaffected security blb assumes that it s running in a protected network and currently does no authentication of network requests data is not encrypted on disk future plans include encrypting data on disk and managing encryption keys in the curator operation because blb stores explicit locations for all data adding storage to a cluster is simple and doesn t require migrating any data future plans include rebalancing existing data across new disks in a slow controlled way removing storage from a cluster is similarly simple an operator can mark disks for draining which will migrate data off of them in a slow controlled way blb exports many detailed metrics about performance and other operational concerns in prometheus format in general blb is designed to heal and recover from routine hardware failures and not bother ops staff with proper configuration it can even replace members of raft groups automatically building and running blb uses the new go module system as a build system so you ll need go 1 11 or later go get github com westerndigitalcorporation blb cmd quick test to test things out quickly you can use blbcli to start a cluster on your local machine and interact with it here s a sample transcript lightly edited to remove irrelevant bits mkdir tmp blb export tmpdir tmp blb echo hello testfile blbcli shell blb start cluster cli go 967 root directory of the cluster tmp blb blbcli231626552 blbcli245145911 cli go 976 log file path tmp blb blbcli231626552 blbcli245145911 log txt cluster go 85 m0 has addr localhost 50883 cluster go 85 m1 has addr localhost 50884 cluster go 85 m2 has addr localhost 50885 cluster go 85 c0 0 has addr localhost 50886 cluster go 85 c0 1 has addr localhost 50887 cluster go 85 c0 2 has addr localhost 50888 cluster go 85 c1 0 has addr localhost 50889 cluster go 85 c1 1 has addr localhost 50890 cluster go 85 c1 2 has addr localhost 50891 cluster go 85 t0 has addr localhost 50892 cluster go 85 t1 has addr localhost 50893 cluster go 85 t2 has addr localhost 50894 cluster go 85 t3 has addr localhost 50895 cluster go 85 t4 has addr localhost 50896 cli go 982 local cluster is started wait 10s little while for raft to set up clusters blb create client go 233 create a blob with opts 3 0 0 0 nil 0 0xc0005c6960 attempt 0 cli go 505 new blob id 0000000100000001 blb write b 0000000100000001 f testfile client go 325 open blob 0000000100000001 attempt 0 blb read b 0000000100000001 client go 325 open blob 0000000100000001 attempt 0 hello blb stat b 0000000100000001 client go 325 open blob 0000000100000001 attempt 0 cli go 532 blob 0000000100000001 repl 3 numtracts 1 bytelen 6 cli go 539 mtime 2018 11 08t15 09 54 08 00 atime 2018 11 08t15 10 02 08 00 cli go 540 expires cli go 541 storagehint default storageclass replicated blb exit testing run testblb from the bin directory to run the suite of integration tests unit tests can be run with the usual go test command production environment master curator and tractserver are the main binaries that you ll need to deploy there are scripts in scripts that have examples for running them they ll need customization for your environment of course a basic cluster would start with three or more tractservers one master group with three replicas and one or more curator groups with three replicas each service discovery several of the environment specific dependencies of blb were stubbed out in this open source release including cluster sniffing what cluster am i running in dynamic configuration and most importantly service discovery the stub service discovery implementation polls dns but for best results you should replace it with something that uses whichever better mechanism is available in your environment e g consul zookeeper or a fancier dns based approach all the platform specific stubs are in the platform directory disks the set of disks managed by the tractserver can be dynamic allowing for hot swapping without restarting the tractserver and interrupting traffic the interface is http over an unix socket details are in internal tractserver disk controller go history blb was originally developed at upthere ut a cloud storage service as the intended storage system for most of our bulk data it ran in production for several months although not as the sole storage system in september 2017 upthere was acquired by western digital wd and it was decided to pause development on blb and move data to other storage systems ut https upthere com wd https www westerndigital com future and contribution although blb is not being actively developed as a production system its authors plan to continue improving the system in their spare time as an educational project if you d like to contribute in any way just file pull requests or issues here on github if you d like to use it as a base for production services we d also like to hear from you some projects we d like to work on expanding the id bit sizes adding object names flat namespace not directories replacing protocol buffers with flatbuffers in the curator database to reduce scan overhead replacing the go rpc system with grpc encryption at rest with end to end checksums speculatively initiate a read from another replica or rs reconstruction while still waiting for a read harden the raft implementation rebalance data onto new tractservers rebalance partitions among curators use the copysets cs algorithm to choose replica sets instead of randomly use raw disks cmr and smr possibly in conjunction with ssds for buffering writes and caching reads using a fancier erasure coding scheme that allows cheaper faster recovery cs https www usenix org conference atc13 technical sessions presentation cidon | os |
|
Natural-Language-Processing-with-Python | natural language processing with python python ile dogal dil isleme lessons course 01 mini nlp tasks preprocessing https github com seraybeser natural language processing with python blob master course 2001 20 20mini 20nlp 20tasks preprocessing py cleaning 1 select only words sadece kelimeleri secmek 2 remove punctuation noktalama isaretlerini silmek 3 normalizing case buyuk kucuk harf normalizasyonunu yapmak 4 remove stopwords stopwords leri kaldirmak 5 remove one length characters tek karakterli kelimeleri silmek 6 remove digits sayilari silmek stemming kelimenin kokune gitme islemi bag of words https github com seraybeser natural language processing with python blob master course 2001 20 20mini 20nlp 20tasks bag of words py bag of words with keras https github com seraybeser natural language processing with python blob master course 2001 20 20mini 20nlp 20tasks bag of words keras py bag of words kelime cantasi bag of words bow is a model used in natural language processing one aim of bow is to categorize documents the idea is to analyse and classify different bags of words corpus and by matching the different categories we identify which bag a certain block of text test data comes from https ongspxm github io blog 2014 12 bag of words natural language processing building a bag of words involves 3 steps kelime cantasi olusturma 3 asamalidir tokenizing counting normalizing kelime cantasi bag of words bow dogal dil islemesinde kullanilan bir modeldir bow un bir amaci belgeleri kategorize etmektir amac farkli canta sozcukleri ni korpus analiz etmek ve siniflandirmaktir farkli kategorilere eslestirerek belirli bir metin blogunun test verisi cantasini tanimlamis oluyoruz natural language processing with python http www nltk org book ch 01 language processing and python ch 02 accessing text corpora and lexical resources ch 03 processing raw text ch 04 writing structured programs ch 05 categorizing and tagging words | nltk natural-language-processing nlp spam-filtering word2vec word-embedding bow word-embeddings bag-of-words | ai |
vowpal_wabbit | img src logo assets vowpal wabbits github logo 3x png height auto width 100 alt vowpal wabbit linux build status https img shields io azure devops build vowpalwabbit 3934113c 9e2b 4dbc 8972 72ab9b9b4342 23 label linux 20build logo azure 20devops https dev azure com vowpalwabbit vowpal 20wabbit build latest definitionid 23 branchname master windows build status https img shields io azure devops build vowpalwabbit 3934113c 9e2b 4dbc 8972 72ab9b9b4342 14 label windows 20build logo azure 20devops https dev azure com vowpalwabbit vowpal 20wabbit build latest definitionid 14 branchname master codecov https codecov io gh vowpalwabbit vowpal wabbit branch master graph badge svg https codecov io gh vowpalwabbit vowpal wabbit total alerts https img shields io lgtm alerts g johnlangford vowpal wabbit svg logo lgtm logowidth 18 https lgtm com projects g johnlangford vowpal wabbit alerts this is the vowpal wabbit fast online learning code why vowpal wabbit vowpal wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online hashing allreduce reductions learning2search active and interactive learning there is a specific focus on reinforcement learning with several contextual bandit algorithms implemented and the online nature lending to the problem well vowpal wabbit is a destination for implementing and maturing state of the art algorithms with performance in mind input format the input format for the learning algorithm is substantially more flexible than might be expected examples can have features consisting of free form text which is interpreted in a bag of words way there can even be multiple sets of free form text in different namespaces speed the learning algorithm is fast similar to the few other online algorithm implementations out there there are several optimization algorithms available with the baseline being sparse gradient descent gd on a loss function scalability this is not the same as fast instead the important characteristic here is that the memory footprint of the program is bounded independent of data this means the training set is not loaded into main memory before learning starts in addition the size of the set of features is bounded independent of the amount of training data using the hashing trick feature interaction subsets of features can be internally paired so that the algorithm is linear in the cross product of the subsets this is useful for ranking problems the alternative of explicitly expanding the features before feeding them into the learning algorithm can be both computation and space intensive depending on how it s handled visit the wiki to learn more https github com vowpalwabbit vowpal wabbit wiki getting started for the most up to date instructions for getting started on windows macos or linux please see the wiki https github com vowpalwabbit vowpal wabbit wiki getting started this includes installing with a package manager https github com vowpalwabbit vowpal wabbit wiki getting started building https github com vowpalwabbit vowpal wabbit wiki building tutorial https github com vowpalwabbit vowpal wabbit wiki tutorial | c-plus-plus machine-learning online-learning contextual-bandits reinforcement-learning active-learning learning-to-search cpp | ai |
flame | p align center img src docs images logo png alt flame logo width 200 p https img shields io badge flame join 20slack brightgreen https join slack com t flame slack shared invite zt 1mprreo9z fmpgb1upi43jofjkyhiqaq fire quickstart ubuntu fire docs quickstart ubuntu md fire quickstart macos fire docs quickstart mac md flame is a platform that enables developers to compose and deploy federated learning fl training workloads easily the system is comprised of a service control plane and a python library data plane the service manages machine learning workloads while the python library facilitates composition of ml workloads and the library is also responsible for executing fl workloads with extensibility of its library flame can support various experimentations and use cases prerequisites the target runtime environment is linux development has been mainly conducted under macos environment one should first set up a development environment for more details refer to here docs prerequisites md this repo has the following directory structure flame code of conduct md contributing md license makefile build makefile readme md api specification of rest api for flame apiserver build configuration files for building flame binaries and container image cmd source files for flame control plane docs document folder examples example folder fiab dev test env in a single box go mod go sum lib python library for core flame data plane lint sh pkg go packages for cmd scripts utility scripts supported algorithms mechanisms method note fedavg https arxiv org pdf 1602 05629 pdf fedyogi https arxiv org pdf 2003 00295 pdf fedadam https arxiv org pdf 2003 00295 pdf fedadagrad https arxiv org pdf 2003 00295 pdf fedprox https arxiv org pdf 1812 06127 pdf fedbuff asynchronous fl https arxiv org pdf 2106 06639 pdf and https arxiv org pdf 2111 04877 pdf secure aggregation is excluded feddyn https arxiv org pdf 2111 04263 pdf oort https arxiv org pdf 2010 06081 pdf client selection algorithm mechanism experimental release hierarchical fl https arxiv org pdf 1905 06641 pdf a simplified version where k sub 2 sub 1 support both synchronous and asynchronous fl hybrid fl a hybrid approach to combine federated learning with ring reduce topology motivated from https openreview net pdf id h0oawl6tha documentation a full document can be found here docs readme md the document will be updated on a regular basis support we welcome feedback questions and issue reports maintainers email address flame github owners cisco com github issues https github com cisco open flame issues new choose citation misc flame2023 title federated learning operations made simple with flame author harshit daga and jaemin shin and dhruv garg and ada gavrilovska and myungjin lee and ramana rao kompella year 2023 eprint 2305 05118 archiveprefix arxiv primaryclass cs lg | os |
|
hls4ml | p float left img src https github com fastmachinelearning fastmachinelearning github io raw master images hls4ml logo svg alt hls4ml width 400 p doi https zenodo org badge 108329371 svg https zenodo org badge latestdoi 108329371 license https img shields io badge license apache 2 0 red svg https opensource org licenses apache 2 0 documentation status https github com fastmachinelearning hls4ml actions workflows build sphinx yml badge svg https fastmachinelearning org hls4ml pypi version https badge fury io py hls4ml svg https badge fury io py hls4ml downloads https static pepy tech personalized badge hls4ml period total units international system left color grey right color orange left text downloads https pepy tech project hls4ml a href https anaconda org conda forge hls4ml img alt conda forge src https img shields io conda dn conda forge hls4ml svg label conda forge a a package for machine learning inference in fpgas we create firmware implementations of machine learning algorithms using high level synthesis language hls we translate traditional open source machine learning package models into hls that can be configured for your use case if you have any questions comments or ideas regarding hls4ml or just want to show us how you use hls4ml don t hesitate to reach us through the discussions https github com fastmachinelearning hls4ml discussions tab documentation tutorial for more information visit the webpage https fastmachinelearning org hls4ml https fastmachinelearning org hls4ml detailed tutorials on how to use hls4ml s various functionalities can be found here https github com hls fpga machine learning hls4ml tutorial installation bash pip install hls4ml to install the extra dependencies for profiling bash pip install hls4ml profiling getting started creating an hls project python import hls4ml fetch a keras model from our example repository this will download our example model to your working directory and return an example configuration file config hls4ml utils fetch example model keras 3layer json you can print the configuration to see some default parameters print config convert it to a hls project hls model hls4ml converters keras to hls config print full list of example models if you want to explore more hls4ml utils fetch example list building a project with xilinx vivado hls after downloading and installing from here https www xilinx com products design tools vivado integration esl design html note vitis hls is not yet supported vivado hls versions between 2018 2 and 2020 1 are recommended python use vivado hls to synthesize the model this might take several minutes hls model build print out the report if you want hls4ml report read vivado report my hls test citation if you use this software in a publication please cite the software bibtex software fastml hls4ml author fastml team title fastmachinelearning hls4ml year 2023 publisher zenodo version v0 7 1 doi 10 5281 zenodo 1201549 url https github com fastmachinelearning hls4ml and first publication bibtex article duarte 2018ite author duarte javier and others title fast inference of deep neural networks in fpgas for particle physics eprint 1804 06913 archiveprefix arxiv primaryclass physics ins det reportnumber fermilab pub 18 089 e doi 10 1088 1748 0221 13 07 p07027 journal jinst volume 13 number 07 pages p07027 year 2018 additionally if you use specific features developed in later papers please cite those as well for example cnns bibtex article aarrestad 2021zos author aarrestad thea and others title fast convolutional neural networks on fpgas with hls4ml eprint 2101 05108 archiveprefix arxiv primaryclass cs lg reportnumber fermilab pub 21 130 scd doi 10 1088 2632 2153 ac0ea1 journal mach learn sci tech volume 2 number 4 pages 045015 year 2021 article ghielmetti 2022ndm author ghielmetti nicol o and others title real time semantic segmentation on fpgas for autonomous vehicles with hls4ml eprint 2205 07690 archiveprefix arxiv primaryclass cs cv reportnumber fermilab pub 22 435 ppd doi 10 1088 2632 2153 ac9cb5 journal mach learn sci tech year 2022 binary ternary networks bibtex article loncar 2020hqp author ngadiuba jennifer and others title compressing deep neural networks on fpgas to binary and ternary precision with hls4ml eprint 2003 06308 archiveprefix arxiv primaryclass cs lg reportnumber fermilab pub 20 167 ppd scd doi 10 1088 2632 2153 aba042 journal mach learn sci tech volume 2 pages 015001 year 2021 acknowledgments if you benefited from participating in our community we ask that you please acknowledge the fast machine learning collaboration and particular individuals who helped you in any publications please use the following text for this acknowledgment we acknowledge the fast machine learning collective as an open community of multi domain experts and collaborators this community and names of individuals in particular were important for the development of this project | hls machine-learning fpga python keras pytorch onnx vivado vivado-hls neural-network intel-hls | ai |
Cola | cola language models are visual reasoning coordinators div align center h2 cola neurips 2023 br large language models are visual reasoning coordinators h2 div align center a href https cliangyu com target blank liangyu chen sup sup a emsp a href https brianboli com target blank bo li sup sup a emsp a href https sincerass github io target blank sheng shen sup sup a emsp a href https jingkang50 github io target blank jingkang yang sup sup a emsp br a href https chunyuan li target blank chunyuan li sup sup a emsp a href https people eecs berkeley edu keutzer target blank kurt keutzer sup sup a emsp a href http people eecs berkeley edu trevor target blank trevor darrell sup sup a emsp a href https liuziwei7 github io target blank ziwei liu sup x2709 sup a div div align center sup sup s lab nanyang technological university br sup sup university of california berkeley emsp sup sup microsoft research redmond br sup sup equal contribution emsp sup sup project lead emsp sup x2709 sup corresponding author div img src https i postimg cc zqxsn8rn sm teaser png h3 tl dr h3 we use a language model lm to aggregate the outputs of 2 vision language models vlms our model assemble approach is named cola coordinative language model or visual reasoning cola is most effective with the lm finetuned termed as cola ft cola is also effective with zero shot or few shot in context learning termed as cola zero beside the performance gain cola is also more robust to the vlms errors we show that cola can be applied to various vlms including large multimodal models like instructblip and 7 datasets vqa v2 ok vqa a okvqa e snli ve vsr clevr gqa and it consistently improves the performance p align center a href https openreview net forum id kdhpwogtx6y target blank arxiv a a href https www youtube com watch v tp5sn8aqyze ab channel aijournalclub target blank talk a english talk coming soon p div environment setup i highly recommend you to update nvidia drivers and cuda to the latest version in case of weird bugs see requirements txt for the environment where the code is tested with shell conda env create f cola yml we use bf16 for inference and finetuning which supports newer gpus prepare datasets and models shell mkdir datasets mkdir predictions mkdir pretrained models below are the datasets we tested you don t have to download all i suggest starting with a okvqa a okvqa download from official page https allenai org project a okvqa home ok vqa download from official page https okvqa allenai org download html vqav2 download from official page https visualqa org download html clevr download from kaggle https www kaggle com datasets timoboz clevr dataset coco gqa download by lavis script https github com salesforce lavis tree main lavis datasets download scripts vsr download from official page https github com cambridgeltl visual spatial reasoning e snli ve flickr30k download from official page https github com maximek3 e vil we convert all the datasets to the format of a okvqa dataset see data utils for conversion scripts shell datasets aokvqa okvqa coco train2017 val2017 test2017 esnlive flicr30k images vsr trainval2017 vqav2 gqa images clevr download ofa model from huggingface other models can be downloaded automatically shell cd git lfs clone https huggingface co ofa sys ofa large inference shell 1 get the plausible answers for the validation set python query query blip py data dir datasets dataset name aokvqa split val vlm task vqa bs 128 prediction out predictions aokvqa blip vqa val da json python query query ofa py vlm model path ofa large data dir datasets dataset name aokvqa split val vlm task vqa bs 128 prediction out predictions aokvqa ofa vqa val da json 2 get the captions for the validation set python query query blip py data dir datasets dataset name aokvqa split val vlm task caption bs 128 prediction out predictions aokvqa blip caption val da json python query query ofa py vlm model path ofa large data dir datasets dataset name aokvqa split val vlm task caption bs 128 prediction out predictions aokvqa ofa caption val da json 3 query the language model cola zero delete incontext num examples 2 for 0 shot inference python query query flan py data dir datasets dataset name aokvqa split val vlm task vqa bs 128 prediction out predictions aokvqa cola2 da json max new tokens 250 llm google flan t5 small vlm1 ofa vlm2 blip include profile include caption include choices incontext num examples 2 anoterh example query mistral 7b with instructblip xl and xxl python query query llm py data dir datasets dataset name aokvqa split val vlm task vqa bs 128 prediction out predictions aokvqa mistral cola2 da json max new tokens 250 llm mistralai mistral 7b v0 1 vlm1 insblipt5xl vlm2 insblipt5xxl include profile include caption include choices incontext num examples 2 anoterh example query mistral 7b on test set of aokvqa python query query llm py data dir datasets dataset name aokvqa split test vlm task vqa bs 128 prediction out predictions aokvqa mistral cola2 test da json max new tokens 250 llm mistralai mistral 7b v0 1 vlm1 insblipt5xl vlm2 insblipt5xxl include profile include caption include choices incontext num examples 2 anoterh example query vicuna 7b on test set of aokvqa python query query llm py data dir datasets dataset name aokvqa split test vlm task vqa bs 16 prediction out predictions aokvqa vicuna cola2 test da json max new tokens 250 llm lmsys vicuna 7b v1 5 16k vlm1 insblipt5xl vlm2 insblipt5xxl include profile include caption include choices incontext num examples 2 4 evaluate the predictions multiple choice see evaluate sh for direct answer evalation export pythonpath export data dir datasets export dataset aokvqa export split val export log dir logs export preds dir predictions export pt model dir pretrained models export prefix aokvqa cola0 python evaluation prepare predictions py data dir data dir dataset dataset split split da preds dir prefix da json mc preds dir prefix mc json out preds dir prefix json python evaluation eval predictions py data dir data dir dataset dataset split split preds preds dir prefix json finetuning shell get the plausible answers and captions for both training and validation sets see step 1 and 2 of inference 1 finetune the language model cola ft delete include choices for direct answer datasets need to wandb login before finetuning export model name aok blip ofa ft wandb run id model name python query finetune flan py data dir datasets dataset name aokvqa split train val split val bs 16 llm google flan t5 xxl vlm1 blip vlm2 ofa prediction out placeholder include profile include caption include choices another example finetune mistral 7b or other decoder only models export model name aok insblipt5xl insblipt5xxl mistral ft wandb run id model name python query finetune llm py data dir datasets dataset name aokvqa split train val split val bs 16 llm mistralai mistral 7b v0 1 vlm1 insblipt5xl vlm2 insblipt5xxl prediction out placeholder include profile include caption include choices 2 query the finetuned model we don t suggest using few shot in context learning for finetuned models python query query flan py data dir datasets dataset name aokvqa split val vlm task vqa bs 128 max new tokens 250 prediction out predictions aokvqa colaft da json max new tokens 250 llm pretrained models model name the epoch you test vlm1 blip vlm2 ofa include choices include profile include caption another example query vicuna model on the test set of aokvqa python query query llm py data dir datasets dataset name aokvqa split test vlm task vqa bs 16 prediction out predictions aokvqa vicuna colaft da json max new tokens 250 llm pretrained models aok insblipt5xl insblipt5xxl vicuna ft lmsys vicuna 7b v1 5 16k language profile bs16 epoch0 vlm1 insblipt5xl vlm2 insblipt5xxl include profile include caption include choices 3 evaluate the evaluation script is the same as step 4 of inference citation if you use this code in your research please kindly cite this work bibtex inproceedings chen2023language title language models are visual reasoning coordinators author liangyu chen and bo li and sheng shen and jingkang yang and chunyuan li and kurt keutzer and trevor darrell and ziwei liu booktitle iclr 2023 workshop on mathematical and empirical understanding of foundation models year 2023 url https openreview net forum id kdhpwogtx6y acknowledgements evaluation code is borrowed from aokvqa https github com allenai aokvqa part of this readme is borrowed from visual prompt retrieval https github com zhangyuanhan ai visual prompt retrieval | ai |
|
homeCare | homecare this is a mobile application development project | front_end |
|
Diabetes-Prediction | diabetes predictor predict diabetes using machine learning in this project our objective is to predict whether the patient has diabetes or not based on various features like glucose level insulin age bmi we will perform all the steps from data gathering to model deployment during model evaluation we compare various machine learning algorithms on the basis of accuracy score metric and find the best one then we create a web app using flask which is a python micro framework read more about it in my blogpost https medium com adityamankar09 building a diabetes predictor 4702b99bc7e4 screenshot screenshot jpg installation clone this repository and unzip it after downloading cd into the flask directory begin a new virtual environment with python 3 and activate it install the required packages using pip install r requirements txt execute the command python app py open http 127 0 0 1 5000 in your browser | python machine-learning flask diabetes-prediction medicine | ai |
FFCV-SSL | p align center h1 b fast forward computer vision for self supervised learning b h1 ffcv ssl is a fork of the ffcv library https github com libffcv ffcv with an added support of self supervised training in this fork you can find the traditional data augmentations used in ssl but also several improvements to handle multiple views of a given image and examples on how to train well known ssl methods like simclr here is an example of the performances one can get on simclr using ffcv ssl img src assets ffcv vs torchvision jpg width 830px please refer to the original ffcv library https github com libffcv ffcv to generate the dataset beton files installation conda create y n ffcv ssl python 3 9 cupy pkg config compilers libjpeg turbo opencv pytorch torchvision torchaudio pytorch cuda 11 7 numba c pytorch c nvidia c conda forge conda activate ffcv ssl pip install e troubleshooting note if the above commands result in a package conflict error try running conda config env set channel priority flexible in the environment and rerunning the installation command what s new a name introduction a multi views ffcv ssl is able to return an arbitraty number of different view of a given field with different pipelines more augmentations data augmentations is crucial for methods like self supervised learning in this fork we add colorjitter solarization grayscale rotation seeding being able to fix the seed of a given transformation is important for reproducibility data augmentations parameters in this fork you can get label pipelines that will return the parameters of the data augmentations that are used how to train simclr using ffcv ssl clone and install this repository then use python examples train ssl py config file examples rn50 configs rn50 baseline yaml data train dataset your train data beton data val dataset your val data beton data num workers 10 data in memory 1 logging folder your checkpoint training batch size 32 training epochs 100 model remove head 0 model mlp 8192 8192 8192 model fc 0 model proj relu 0 training loss simclr dist use submitit 0 training optimizer adamw training base lr 0 0005 0 this script allow also the use of submitit which can generate a sbatch file to send this job on a slurm cluster to activate submit you just need to add the argument dist use submitit 1 this script support other ssl loss such that vicreg barlow twins and byol to use other loss you ll just need to replace training loss simclr by training loss vicreg multiview augmentation e g for ssl a name multiview a to run the examples you ll need to setup the following environment variable export ffcv datat path your path to the path of your ffcv beton file then you can try this code examples test ffcv augmentations ssl py we show how to produce three views from a dataset generated with only two fields image and label in short we use the loader s custom field mapper argument to give a dictionnary mapping the extra given pipelines to the ones present in the saved dataset ffcv seeding a name seeding a for seeding you can try this code examples test ffcv augmentations seeding py located in the examples folder by default the loader and das have a none seed i e different runs have different data ordering and augmentaiton realizations as shown below for a mini batch size of 3 on imagenet only with random crop and translation as das for reproducibility we enable seed specification for both the loader and each da leading to the follow where both are set return the parameters of a data augmentation a name params da a you can find a working example in this code examples ffcv test cropping with labels py to get the parameters of a crops i e the bounding boxe used to extract the crop you can use seeding in addition of a labelling pipeline here is an example of such pipeline where we fixe the seed to 5 image pipeline ffcv transforms randomresizedcrop output size 224 224 ratio 0 4 1 0 seed 5 scale 0 08 1 0 totensor todevice ch device cuda 0 non blocking true totorchimage normalizeimage imagenet mean imagenet std np float16 and the corresponding label pipeline label crops pipeline ffcv transforms labelrandomresizedcrop output size 224 224 ratio 0 4 1 0 seed 5 scale 0 08 1 0 totensor squeeze todevice ch device cpu non blocking true in order to get parameters that are consistent with the transformations applied on the images it s really important that both the image and label pipeline get the exact same parameters with the same seed furthermore when creating the dataloader you should specify a custom fiel mapper with the label crops pipeline on the image which is important to get the original width height size of the image such as custom field mapper crop parameters image citation if you use ffcv ssl please cite it as misc bordes2023ffcv ssl doi 10 48550 arxiv 2303 01986 url https arxiv org abs 2303 01986 author bordes florian and balestriero randall and vincent pascal keywords machine learning cs lg fos computer and information sciences fos computer and information sciences title towards democratizing joint embedding self supervised learning publisher arxiv year 2023 copyright arxiv org perpetual non exclusive license misc leclerc2022ffcv author guillaume leclerc and andrew ilyas and logan engstrom and sung min park and hadi salman and aleksander madry title ffcv year 2022 howpublished url https github com libffcv ffcv note commit xxxxxxx make sure to replace xxxxxxx above with the hash of the commit used license this project is released as the original repository under apache 2 0 license see license license for details | ai |
|
component-gallery | p align center a href https component gallery img alt src https github com inbn component gallery raw master src images favicon png width 60 a p h1 align center the component gallery h1 this project is based on gatsby starter default https www gatsbyjs org starters gatsbyjs gatsby starter default quick start 1 create env file duplicate the file env example in the root of the project and call it env development you ll need to add values for airtable api key and airtable base id important note the full airtable database this project uses is private but there s an example with enough data to get started with here https airtable com shrsiqxyks0mo53jy click the copy base link in the top right to get your own version 1 install dependencies sh npm install 1 start developing sh npm start 1 open the source code and start editing your site is now running at http localhost 8000 note you ll also see a second link http localhost 8000 graphql this is a tool you can use to experiment with querying your data learn more about using this tool in the gatsby tutorial https www gatsbyjs org tutorial part five introducing graphiql what s inside a quick look at the top level files and directories you ll see in a gatsby project node modules src gitignore gatsby browser js gatsby config js gatsby node js gatsby ssr js license package lock json package json readme md 1 node modules this directory contains all of the modules of code that your project depends on npm packages are automatically installed 2 src this directory will contain all of the code related to what you will see on the front end of your site what you see in the browser such as your site header or a page template src is a convention for source code 3 gitignore this file tells git which files it should not track not maintain a version history for 4 prettierrc this is a configuration file for prettier https prettier io prettier is a tool to help keep the formatting of your code consistent 5 gatsby browser js this file is where gatsby expects to find any usage of the gatsby browser apis https www gatsbyjs org docs browser apis if any these allow customization extension of default gatsby settings affecting the browser 6 gatsby config js this is the main configuration file for a gatsby site this is where you can specify information about your site metadata like the site title and description which gatsby plugins you d like to include etc check out the config docs https www gatsbyjs org docs gatsby config for more detail 7 gatsby node js this file is where gatsby expects to find any usage of the gatsby node apis https www gatsbyjs org docs node apis if any these allow customization extension of default gatsby settings affecting pieces of the site build process 8 gatsby ssr js this file is where gatsby expects to find any usage of the gatsby server side rendering apis https www gatsbyjs org docs ssr apis if any these allow customization of default gatsby settings affecting server side rendering 9 license gatsby is licensed under the mit license 10 package lock json see package json below first this is an automatically generated file based on the exact versions of your npm dependencies that were installed for your project you won t change this file directly 11 package json a manifest file for node js projects which includes things like metadata the project s name author etc this manifest is how npm knows which packages to install for your project 12 readme md a text file containing useful reference information about your project learning gatsby looking for more guidance full documentation for gatsby lives on the website https www gatsbyjs org here are some places to start for most developers we recommend starting with our in depth tutorial for creating a site with gatsby https www gatsbyjs org tutorial it starts with zero assumptions about your level of ability and walks through every step of the process to dive straight into code samples head to our documentation https www gatsbyjs org docs in particular check out the guides api reference and advanced tutorials sections in the sidebar deploy deploy to netlify https www netlify com img deploy button svg https app netlify com start deploy repository https github com gatsbyjs gatsby starter default | os |
|
noGuilt-KeepPracticing | this is a project where i keep practicing my coding skills and storing them for future reference | cloud |
|
club-resources | important notice all of the markdown files for this repository have been put onto the club website https ufosc org any further changes should be made in the club docs repo instead https github com ufosc osc docs club resources this is a collection of references links and other information about various programming languages technology and other things the club works with goals 1 have a single source of information the club can reference 2 that people can contribute links and tidbits they found useful to help others 3 projects will link directly to these files to not duplicate work each file or folder has information about that technology as well as a set of useful links to other good learning resources somethings have folders that will contain additional files for club wide code styling or more in depth information there is also a generic style guidelines md generic style guidelines md that serves as the base for the clubs styling preferences as well as the coding best practices md coding best practices md that suggests best practices for programming that we suggest everyone read contributing we want your help in filling out the repository if you have a link you really liked or see that we are missing files about something please help us please read contributing md contributing md for how to work on the project license this project is licensed under the cc by 4 0 see the license md license md file for details | resources learning programming-languages technology | server |
steem | steem the blockchain that will tokenize the web welcome to the official repository for steem the blockchain that will revolutionize the web and soon the blockchain for smart media tokens steem is the first blockchain which introduced the proof of brain social consensus algorithm for token allocation being one of the most actively developed blockchain projects currently in existence it s become fertile soil for entrepreneurial pursuits it has also become home for many cryptocurrency centric projects steem aims to be the preferred blockchain for dapp development with smart media tokens at its core with smts everyone can leverage the power of steem originally steem was announced on the bitcointalk forum https bitcointalk org index php topic 1410943 new prior to the start of any mining steem is currently not mineable documents whitepaper steem io steemwhitepaper pdf https steem io steemwhitepaper pdf bluepaper steem io steembluepaper pdf https steem io steem bluepaper pdf smt whitepaper steem io smtwhitepaper pdf https smt steem io smt whitepaper pdf not final developer portal https developers steem io advantages free transactions resource credits freemium model fast block confirmations 3 seconds time delay security vested steem savings hierarchical role based permissions keys integrated token allocation smart media tokens soon lowest entry barrier for user adoption in the market dozens of dapps already built on steem and many more to come technical details currency symbol steem sbd steem s very own stable coin with a one way peg delegated proof of stake consensus dpos 10 apr inflation narrowing to 1 apr over 20 years 75 of inflation to proof of brain social consensus algorithm 15 of inflation to stakeholders 10 of inflation to block producers installation getting started with steem is fairly simple you can either choose to use docker images build with docker manually or build from source directly all steps have been documented and while many different os are supported the easiest one is ubuntu 16 04 quickstart just want to get up and running quickly we have pre built docker images for your convenience more details are in our quickstart guide https github com steemit steem blob master doc exchangequickstart md building we strongly recommend using one of our pre built docker images or using docker to build steem both of these processes are described in the quickstart guide https github com steemit steem blob master doc exchangequickstart md but if you would still like to build from source we also have build instructions https github com steemit steem blob master doc building md for linux ubuntu lts and macos dockerized p2p node to run a p2p node ca 2gb of memory is required at the moment docker run d p 2001 2001 p 8090 8090 name steemd default steemit steem docker logs f steemd default follow along dockerized full node to run a node with all the data e g for supporting a content website ca 14gb of memory and growing is required docker run env use way too much ram 1 env use full web node 1 d p 2001 2001 p 8090 8090 name steemd full steemit steem docker logs f steemd full cli wallet we provide a basic cli wallet for interfacing with steemd the wallet is self documented via command line help the node you connect to via the cli wallet needs to be running the account by key api condenser api and needs to be configured to accept websocket connections via webserver ws endpoint testing see doc devs testing md doc devs testing md for test build targets and info on how to use lcov to check code test coverage configuration config file run steemd once to generate a data directory and config file the default location is witness node data dir kill steemd it won t do anything without seed nodes if you want to modify the config to your liking we have two example configs used in the docker images consensus node contrib config for docker ini full node contrib fullnode config ini all options will be present in the default config file and there may be more options needing to be changed from the docker configs some of the options actually used in images are configured via command line seed nodes a list of some seed nodes to get you started can be found in doc seednodes txt doc seednodes txt this same file is baked into the docker images and can be overridden by setting steemd seed nodes in the container environment at docker run time to a whitespace delimited list of seed nodes with port environment variables there are quite a few environment variables that can be set to run steemd in different ways use way too much ram if set to true steemd starts a full node use full web node if set to true a default config file will be used that enables a full set of api s and associated plugins use nginx frontend if set to true this will enable an nginx reverse proxy in front of steemd that proxies websocket requests to steemd this will also enable a custom healthcheck at the path health that lists how many seconds away from current blockchain time your node is it will return a 200 if it s less than 60 seconds away from being synced use multicore readonly if set to true this will enable steemd in multiple reader mode to take advantage of multiple cores if available read requests are handled by the read only nodes and write requests are forwarded back to the single writer node automatically nginx load balances all requests to the reader nodes 4 per available core this setting is still considered experimental and may have trouble with some api calls until further development is completed home set this to the path where you want steemd to store it s data files block log shared memory config file etc by default var lib steemd is used and exists inside the docker container if you want to use a different mount point like a ramdisk or a different drive then you may want to set this variable to map the volume to your docker container paas mode steemd now supports a paas mode platform as a service that currently works with amazon s elastic beanstalk service it can be launched using the following environment variables use paas if set to true steemd will launch in a format that works with aws eb containers will exit upon failure so that they can be relaunched automatically by ecs this mode assumes use way too much ram and use full web node they do not need to be also set s3 bucket set this to the name of the s3 bucket where you will store shared memory files for steemd in amazon s3 they will be stored compressed in bz2 format with the file name blockchain version latest tar bz2 where version is the release number followed by the git short commit hash stored in each docker image at etc steemdversion sync to s3 if set to true the node will function to only generate shared memory files and upload them to the specified s3 bucket this makes fast deployments and autoscaling for steemd possible system requirements for a full web node you need at least 110gb of disk space available steemd uses a memory mapped file which currently holds 56gb of data and by default is set to use up to 80gb the block log of the blockchain itself is a little over 27gb it s highly recommended to run steemd on a fast disk such as an ssd or by placing the shared memory files in a ramdisk and using the shared file dir path command line option to specify where at least 16gb of memory is required for a full web node seed nodes p2p mode can run with as little as 4gb of memory with a 24 gb state file any cpu with decent single core performance should be sufficient steemd is constantly growing as of august 2017 these numbers were accurate but you may find you need more disk space to run a full node we are also constantly working on optimizing steem s use of disk space on linux use the following virtual memory configuration for the initial sync and subsequent replays it is not needed for normal operation echo 75 sudo tee proc sys vm dirty background ratio echo 1000 sudo tee proc sys vm dirty expire centisecs echo 80 sudo tee proc sys vm dirty ratio echo 30000 sudo tee proc sys vm dirty writeback centisecs no support no warranty the software is provided as is without warranty of any kind express or implied including but not limited to the warranties of merchantability fitness for a particular purpose and noninfringement in no event shall the authors or copyright holders be liable for any claim damages or other liability whether in an action of contract tort or otherwise arising from out of or in connection with the software or the use or other dealings in the software | steemit steem blockchain p2p-node social-network cpp | blockchain |
emotion | emotion detector the goal of this project is to leverage existing open source tools to quickly train a deep learning model that detects emotions from human faces this repo offers tools to scrape a dataset from google images and leverage the queries to label the images apply and fine tune pretrained models to detect faces and serve as the starting point for the model use the trained model to detect and identify emotions in images and videos the five target emotions that will be detected are 1 angry 2 disgusted 3 happy 4 sad 5 surprised for a detailed discussion of this project see this accompanying blog post https medium com swlh training an emotion detector with transfer learning 91dea84adeed labeled harry potter png https github com martin chobanyan emotion blob master resources labeled harry potter png data collection once the fer dataset https www kaggle com c challenges in representation learning facial expression recognition challenge data is downloaded unpack fer data py can be used to extract process and store these images in a directory in addition to these images download data py can be used to scrape data from google images and use the keywords to label the downloaded images this is done using the google images download https google images download readthedocs io en latest installation html library fine tuning a pretrained imagenet model the base model for this project is a resnet model pretrained on imagenet from torchvision this model will be fine tuned later on in the pipeline to detect emotions from faces before this is done the pretrained model is altered to accept single channel grayscale images and then fine tuned such that its output embedding for a grayscale image closely matches the output of the vanilla model with the rgb version of the same image see finetune gray imagenet py for this code the google images scraper can again be leveraged to pull down a small fake sample of imagenet by querying for a handful of images for each imagenet label again see download data py for the code see this file https gist github com yrevar 942d3a0ac09ec9e5eb3a for all 1000 imagenet labels fine tuning on the fer dataset the next step is to fine tune the model to detect emotions in the fer dataset note the fear and neutral images were removed from this dataset in order to align with the images scraped from the internet see finetune fer py for this code fine tuning on the scraped google images in order to remove unnecessary features from the scraped data the images are transformed into single channel grayscale images and are cropped such that each image contains only a single human face the latter step is performed by applying a pretrained mtcnn face detection model to detect and return a bounding box of each face in an image this model comes from the facenet pytorch https github com timesler facenet pytorch library the code for the final training pipeline on the scraped images can be found in finetune emotion py applying the models most of the tools used to initialize define and train the models for this project can be found in model py detect emotions py is a command line script that loads a checkpoint of the fully trained model and applies it to detect emotions within a target image requirements google images download facenet pytorch numpy pandas pillow torch torchvision tqdm installation see this page https google images download readthedocs io en latest installation html for details on how to install the google images download library in particular selenium and a google chrome driver must be downloaded https google images download readthedocs io en latest troubleshooting html installing the chromedriver with selenium in order to query for more images | ai |
|
sws | sws sws simple web server designed for static web pages for internal network use or small embedded systems developed on linux and c | os |
|
Chatbot-AI | overview this is an attempt at implementing sequence to sequence learning with neural networks seq2seq http arxiv org abs 1409 3215 and reproducing the results in a neural conversational model http arxiv org abs 1506 05869 aka the google chatbot the model is based on two lstm https en wikipedia org wiki long short term memory layers one for encoding the input sentence into a thought vector and another for decoding that vector into a response this model is called sequence to sequence or seq2seq this the code for build a chatbot on youtube https www youtube com watch v 5 sarosvc0e feature youtu be seq2seq https 4 bp blogspot com aars0l1pjhq vjj71pkaaei aaaaaaaaaxe nvy1fsbd vs s640 2tfstaticgraphic alt 01 png source http googleresearch blogspot ca 2015 11 computer respond to this email html dependencies 1 install torch http torch ch docs getting started html 2 install the following additional lua libs sh luarocks install nn luarocks install rnn luarocks install penlight to train with cuda install the latest cuda drivers toolkit and run sh luarocks install cutorch luarocks install cunn to train with opencl install the lastest opencl torch lib sh luarocks install cltorch luarocks install clnn 3 download the cornell movie dialogs corpus http www mpi sws org cristian cornell movie dialogs corpus html and extract all the files into data cornell movie dialogs basic usage here s a sample conversation after training for 20 epoch with 50000 examples using the following command sh th train lua cuda dataset 50000 hiddensize 1000 took 3 days to train on my geforce gtx 780m for opencl use opencl instead of cuda to train on cpu don t provide any of those two use the dataset number option to control the size of the dataset training on the full dataset takes about 5h for a single epoch the model will be saved to data model t7 after each epoch if it has improved error decreased me hello bot hi me how are you bot i m fine me what s your name bot it s hard to describe me how so bot i m not sure me what color is the sky bot it s blue me what is your job bot it s not that i m a fucking werewolf me what is the purpose of life bot a gift me are you intelligent bot yes well me are you a machine bot that s a lie me are you human bot no i m not me what are you bot i m not sure to load the model and have a conversation sh th i eval lua cuda skip cuda if you didn t train with it th say hello credits credit for the vast majority of code here goes to marc andr cournoyer https github com macournoyer i ve merely created a wrapper around all of the important functions to get people started | ai |
|
2019_FPGA_Design | undergraduate course fpga design this repository provides various fpga design tutorials tool vivado 2018 3 https www xilinx com support download index html content xilinx en downloadnav vivado design tools 2018 3 html fpga development board pynq z2 board http www tul com tw productspynq z2 html learning resource xilinx online video https www xilinx com video html digilent programmable logic tutorials https reference digilentinc com learn programmable logic tutorials start zynq 7000 all programmable soc embedded design tutorial https ppt cc f4leqx vivado design suite user guide https ppt cc fyfdxx appendix a references pynq http www pynq io github learning resource 30 git https ithelp ithome com tw users 20004901 ironman 525 git cheat sheet https services github com on demand downloads github git cheat sheet pdf git help systemverilog ieee standard for systemverilog https ieeexplore ieee org document 8299595 verilog ieee standard for verilog https ieeexplore ieee org document 1620780 teaching assistance fpga fpga homework3 problem1 n26074906 mail ncku edu tw n26084723 mail ncku edu tw | os |
|
Blockchain-C-Plus-Plus-Example | blockchain c plus plus example this is a simple example of how a blockchain works in c it follows my video on blockchain here https www youtube com watch v xwkqyojn9yg disclaimer i m in no way an expert in blockchain this is a very contrived and simple example if you notice an error or anything that is amiss feel free to submit a pull request | blockchain |
|
Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials | new list 2023 2024 machine learning deep learning ai web3 tutorials hi thanks for dropping by br br i will be updating this tutorials site on a b daily basis b adding all relevant topcis for 2022 2024 especially pertaining to gpu programming data centric ai emerging topics like sustainable ai with web3ai js defi dao nft and much more br note all these tutorials are supported and accelerated on nvidia gpus br more importantly the applications of ml dl ai into industry areas such as transportation medicine healthcare etc will be something i ll watch with keen interest and would love to share the same with you br finally it is your help i will seek to make it more useful and less boring so please do suggest comment contribute p align center img src https github com tarrysingh artificial intelligence deep learning machine learning tutorials blob master images dk png p index deep learning deep learning uber pyro uber pyro probabalistic tutorials netflix vectorflow netflix vectorflow tutorials pytorch pytorch tutorials tensorflow tensor flow tutorials theano theano tutorials keras keras tutorials caffe deep learning misc torch lua mxnet scikit learn scikit learn statistical inference scipy statistical inference scipy pandas pandas matplotlib matplotlib numpy numpy python data python data kaggle and business analyses kaggle and business analyses spark spark mapreduce python mapreduce python amazon web services aws command lines commands misc misc notebook installation notebook installation curated list of deep learning ai blogs curated list of deeplearning blogs credits credits contributing contributing contact info contact info license license deep learning ipython notebook s and other programming tools such as torch lua d lang in demonstrating deep learning functionality uber pyro probabalistic tutorials p align center img src https github com tarrysingh artificial intelligence deep learning machine learning tutorials blob master images pyro png p additional pyro tutorials pyro examples full examples http pyro ai examples pyro examples variational autoencoders http pyro ai examples vae html pyro examples bayesian regression http pyro ai examples bayesian regression html pyro examples deep markov model http pyro ai examples dmm html pyro examples air attend infer repeat http pyro ai examples air html pyro examples semi supervised ve http pyro ai examples ss vae html pyro examples gmm http pyro ai examples gmm html pyro examples gaussian process http pyro ai examples gp html pyro examples bayesian optimization http pyro ai examples bo html full pyro code https github com tarrysingh artificial intelligence deep learning machine learning tutorials tree master deep learning uber pyro netflix vectorflow tutorials p align center img src https github com tarrysingh artificial intelligence deep learning machine learning tutorials blob master images vectorflow png p mnist example running with dlang https github com netflix vectorflow tree master examples pytorch tutorials p align center img src https github com tarrysingh artificial intelligence deep learning machine learning tutorials blob master images pytorch png p level description beginners zakizhou https github com pytorch tutorials tree master beginner source learning the basics of pytorch from facebook intermedia quanvuong https github com pytorch tutorials tree master intermediate source learning the intermediate stuff about pytorch of from facebook advanced chsasank https github com pytorch tutorials tree master advanced source learning the advanced stuff about pytorch of from facebook learning pytorch by examples numpy tensors and autograd https github com tarrysingh artificial intelligence deep learning machine learning tutorials tree master pytorch at its core pytorch provides two main features an n dimensional tensor similar to numpy but can run on gpus and automatic differentiation for building and training neural networks pytorch getting to know autograd variable gradient neural network https github com tarrysingh artificial intelligence deep learning machine learning tutorials blob master pytorch pytorch 20nn 20basics 20 20autograd 20gradient 20neural 20network 20loss 20backprop ipynb here we start with ultimate basics of tensors wrap a tensor with variable module play with nn module and implement forward and backward function tensor flow tutorials br p align center img src https avatars0 githubusercontent com u 15658638 v 3 s 100 p additional tensorflow tutorials pkmital tensorflow tutorials https github com pkmital tensorflow tutorials nlintz tensorflow tutorials https github com nlintz tensorflow tutorials alrojo tensorflow tutorial https github com alrojo tensorflow tutorial binroot tensorflow book https github com binroot tensorflow book notebook description tsf basics http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow examples notebooks 1 intro basic operations ipynb learn basic operations in tensorflow a library for various kinds of perceptual and language understanding tasks from google tsf linear http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow examples notebooks 2 basic classifiers linear regression ipynb implement linear regression in tensorflow tsf logistic http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow examples notebooks 2 basic classifiers logistic regression ipynb implement logistic regression in tensorflow tsf nn http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow examples notebooks 2 basic classifiers nearest neighbor ipynb implement nearest neighboars in tensorflow tsf alex http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow examples notebooks 3 neural networks alexnet ipynb implement alexnet in tensorflow tsf cnn http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow examples notebooks 3 neural networks convolutional network ipynb implement convolutional neural networks in tensorflow tsf mlp http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow examples notebooks 3 neural networks multilayer perceptron ipynb implement multilayer perceptrons in tensorflow tsf rnn http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow examples notebooks 3 neural networks recurrent network ipynb implement recurrent neural networks in tensorflow tsf gpu http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow examples notebooks 4 multi gpu multigpu basics ipynb learn about basic multi gpu computation in tensorflow tsf gviz http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow examples notebooks 5 ui graph visualization ipynb learn about graph visualization in tensorflow tsf lviz http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow examples notebooks 5 ui loss visualization ipynb learn about loss visualization in tensorflow tensor flow exercises notebook description tsf not mnist http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow exercises 1 notmnist ipynb learn simple data curation by creating a pickle with formatted datasets for training development and testing in tensorflow tsf fully connected http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow exercises 2 fullyconnected ipynb progressively train deeper and more accurate models using logistic regression and neural networks in tensorflow tsf regularization http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow exercises 3 regularization ipynb explore regularization techniques by training fully connected networks to classify notmnist characters in tensorflow tsf convolutions http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow exercises 4 convolutions ipynb create convolutional neural networks in tensorflow tsf word2vec http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow exercises 5 word2vec ipynb train a skip gram model over text8 data in tensorflow tsf lstm http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning tensor flow exercises 6 lstm ipynb train a lstm character model over text8 data in tensorflow br p align center img src http www deeplearning net software theano static theano logo allblue 200x46 png p theano tutorials notebook description theano intro http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning theano tutorial intro theano intro theano ipynb intro to theano which allows you to define optimize and evaluate mathematical expressions involving multi dimensional arrays efficiently it can use gpus and perform efficient symbolic differentiation theano scan http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning theano tutorial scan tutorial scan tutorial ipynb learn scans a mechanism to perform loops in a theano graph theano logistic http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning theano tutorial intro theano logistic regression ipynb implement logistic regression in theano theano rnn http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning theano tutorial rnn tutorial simple rnn ipynb implement recurrent neural networks in theano theano mlp http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning theano tutorial theano mlp theano mlp ipynb implement multilayer perceptrons in theano br p align center img src http i imgur com l45q8c2 jpg p keras tutorials notebook description keras keras is an open source neural network library written in python it is capable of running on top of either tensorflow or theano setup https github com leriomaggio deep learning keras tensorflow blob master readme md learn about the tutorial goals and how to set up your keras environment intro deep learning ann https github com leriomaggio deep learning keras tensorflow blob master 1 20ann 1 1 20introduction 20 20deep 20learning 20and 20ann ipynb get an intro to deep learning with keras and artificial neural networks ann perceptrons and adaline https github com leriomaggio deep learning keras tensorflow blob master 1 20ann 1 1 1 20perceptron 20and 20adaline ipynb implement peceptron and adaptive linear neurons mlp and mnist data https github com leriomaggio deep learning keras tensorflow blob master 1 20ann 1 1 2 20mlp 20and 20mnist ipynb classifying handwritten digits implement mlp train and debug ann theano http nbviewer ipython org github leriomaggio deep learning keras tensorflow blob master 1 2 20introduction 20 20theano ipynb learn about theano by working with weights matrices and gradients keras otto http nbviewer ipython org github leriomaggio deep learning keras tensorflow blob master 1 3 20introduction 20 20keras ipynb learn about keras by looking at the kaggle otto challenge ann mnist http nbviewer ipython org github leriomaggio deep learning keras tensorflow blob master 1 4 20 extra 20a 20simple 20implementation 20of 20ann 20for 20mnist ipynb review a simple implementation of ann for mnist using keras conv nets http nbviewer ipython org github leriomaggio deep learning keras tensorflow blob master 2 1 20supervised 20learning 20 20convnets ipynb learn about convolutional neural networks cnns with keras conv net 1 http nbviewer ipython org github leriomaggio deep learning keras tensorflow blob master 2 2 1 20supervised 20learning 20 20convnet 20handson 20part 20i ipynb recognize handwritten digits from mnist using keras part 1 conv net 2 http nbviewer ipython org github leriomaggio deep learning keras tensorflow blob master 2 2 2 20supervised 20learning 20 20convnet 20handson 20part 20ii ipynb recognize handwritten digits from mnist using keras part 2 keras models http nbviewer ipython org github leriomaggio deep learning keras tensorflow blob master 2 3 20supervised 20learning 20 20famous 20models 20with 20keras ipynb use pre trained models such as vgg16 vgg19 resnet50 and inception v3 with keras auto encoders https github com leriomaggio deep learning keras tensorflow blob master 6 20autoencoders 20and 20embeddings 6 1 20autoencoders 20and 20embeddings ipynb learn about autoencoders with keras rnn lstm https github com leriomaggio deep learning keras tensorflow blob master 7 20recurrent 20neural 20networks 7 1 20rnn 20and 20lstm ipynb learn about recurrent neural networks rnns with keras lstm sentence gen https github com leriomaggio deep learning keras tensorflow blob master 7 20recurrent 20neural 20networks 7 2 20lstm 20for 20sentence 20generation ipynb learn about rnns using long short term memory lstm networks with keras nlp deep learning https github com leriomaggio deep learning keras tensorflow blob master 6 20autoencoders 20and 20embeddings 6 2 20nlp 20and 20deep 20learning ipynb learn about nlp using ann artificial neural networks hyperparamter tuning https github com leriomaggio deep learning keras tensorflow blob master 5 20hyperparameter 20tuning 20and 20transfer 20learning 5 1 20hyperparameter 20tuning ipynb hyperparamters tuning using keras wrapper scikit learn deep learning misc notebook description deep dream http nbviewer ipython org github tarrysingh machine learning tutorials blob master deep learning deep dream dream ipynb caffe based computer vision program which uses a convolutional neural network to find and enhance patterns in images br p align center img src https raw githubusercontent com donnemartin data science ipython notebooks master images scikitlearn png p scikit learn ipython notebook s demonstrating scikit learn functionality notebook description intro http nbviewer ipython org github tarrysingh machine learning tutorials blob master scikit learn scikit learn intro ipynb intro notebook to scikit learn scikit learn adds python support for large multi dimensional arrays and matrices along with a large library of high level mathematical functions to operate on these arrays knn http nbviewer ipython org github tarrysingh machine learning tutorials blob master scikit learn scikit learn intro ipynb k nearest neighbors classifier implement k nearest neighbors in scikit learn linear reg http nbviewer ipython org github tarrysingh machine learning tutorials blob master scikit learn scikit learn linear reg ipynb implement linear regression in scikit learn svm http nbviewer ipython org github tarrysingh machine learning tutorials blob master scikit learn scikit learn svm ipynb implement support vector machine classifiers with and without kernels in scikit learn random forest http nbviewer ipython org github tarrysingh machine learning tutorials blob master scikit learn scikit learn random forest ipynb implement random forest classifiers and regressors in scikit learn k means http nbviewer ipython org github tarrysingh machine learning tutorials blob master scikit learn scikit learn k means ipynb implement k means clustering in scikit learn pca http nbviewer ipython org github tarrysingh machine learning tutorials blob master scikit learn scikit learn pca ipynb implement principal component analysis in scikit learn gmm http nbviewer ipython org github tarrysingh machine learning tutorials blob master scikit learn scikit learn gmm ipynb implement gaussian mixture models in scikit learn validation http nbviewer ipython org github tarrysingh machine learning tutorials blob master scikit learn scikit learn validation ipynb implement validation and model selection in scikit learn br p align center img src https raw githubusercontent com donnemartin data science ipython notebooks master images scipy png p statistical inference scipy ipython notebook s demonstrating statistical inference with scipy functionality notebook description scipy scipy is a collection of mathematical algorithms and convenience functions built on the numpy extension of python it adds significant power to the interactive python session by providing the user with high level commands and classes for manipulating and visualizing data effect size http nbviewer ipython org github tarrysingh machine learning tutorials blob master scipy effect size ipynb explore statistics that quantify effect size by analyzing the difference in height between men and women uses data from the behavioral risk factor surveillance system brfss to estimate the mean and standard deviation of height for adult women and men in the united states sampling http nbviewer ipython org github tarrysingh machine learning tutorials blob master scipy sampling ipynb explore random sampling by analyzing the average weight of men and women in the united states using brfss data hypothesis http nbviewer ipython org github tarrysingh machine learning tutorials blob master scipy hypothesis ipynb explore hypothesis testing by analyzing the difference of first born babies compared with others br p align center img src https raw githubusercontent com donnemartin data science ipython notebooks master images pandas png p pandas ipython notebook s demonstrating pandas functionality notebook description pandas http nbviewer ipython org github tarrysingh machine learning tutorials blob master pandas pandas ipynb software library written for data manipulation and analysis in python offers data structures and operations for manipulating numerical tables and time series github data wrangling https github com donnemartin viz blob master githubstats data wrangling ipynb learn how to load clean merge and feature engineer by analyzing github data from the viz https github com donnemartin viz repo introduction to pandas http nbviewer jupyter org github tarrysingh machine learning tutorials blob master pandas 03 00 introduction to pandas ipynb introduction to pandas introducing pandas objects http nbviewer jupyter org github tarrysingh machine learning tutorials blob master pandas 03 01 introducing pandas objects ipynb learn about pandas objects data indexing and selection http nbviewer jupyter org github tarrysingh machine learning tutorials blob master pandas 03 02 data indexing and selection ipynb learn about data indexing and selection in pandas operations in pandas http nbviewer jupyter org github tarrysingh machine learning tutorials blob master pandas 03 03 operations in pandas ipynb learn about operating on data in pandas missing values http nbviewer jupyter org github tarrysingh machine learning tutorials blob master pandas 03 04 missing values ipynb learn about handling missing data in pandas hierarchical indexing http nbviewer jupyter org github tarrysingh machine learning tutorials blob master pandas 03 05 hierarchical indexing ipynb learn about hierarchical indexing in pandas concat and append http nbviewer jupyter org github tarrysingh machine learning tutorials blob master pandas 03 06 concat and append ipynb learn about combining datasets concat and append in pandas merge and join http nbviewer jupyter org github tarrysingh machine learning tutorials blob master pandas 03 07 merge and join ipynb learn about combining datasets merge and join in pandas aggregation and grouping http nbviewer jupyter org github tarrysingh machine learning tutorials blob master pandas 03 08 aggregation and grouping ipynb learn about aggregation and grouping in pandas pivot tables http nbviewer jupyter org github tarrysingh machine learning tutorials blob master pandas 03 09 pivot tables ipynb learn about pivot tables in pandas working with strings http nbviewer jupyter org github tarrysingh machine learning tutorials blob master pandas 03 10 working with strings ipynb learn about vectorized string operations in pandas working with time series http nbviewer jupyter org github tarrysingh machine learning tutorials blob master pandas 03 11 working with time series ipynb learn about working with time series in pandas performance eval and query http nbviewer jupyter org github tarrysingh machine learning tutorials blob master pandas 03 12 performance eval and query ipynb learn about high performance pandas eval and query in pandas br p align center img src https raw githubusercontent com donnemartin data science ipython notebooks master images matplotlib png p matplotlib ipython notebook s demonstrating matplotlib functionality notebook description matplotlib http nbviewer ipython org github tarrysingh machine learning tutorials blob master matplotlib matplotlib ipynb python 2d plotting library which produces publication quality figures in a variety of hardcopy formats and interactive environments across platforms matplotlib applied http nbviewer ipython org github tarrysingh machine learning tutorials blob master matplotlib matplotlib applied ipynb apply matplotlib visualizations to kaggle competitions for exploratory data analysis learn how to create bar plots histograms subplot2grid normalized plots scatter plots subplots and kernel density estimation plots introduction to matplotlib http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 00 introduction to matplotlib ipynb introduction to matplotlib simple line plots http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 01 simple line plots ipynb learn about simple line plots in matplotlib simple scatter plots http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 02 simple scatter plots ipynb learn about simple scatter plots in matplotlib errorbars ipynb http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 03 errorbars ipynb learn about visualizing errors in matplotlib density and contour plots http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 04 density and contour plots ipynb learn about density and contour plots in matplotlib histograms and binnings http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 05 histograms and binnings ipynb learn about histograms binnings and density in matplotlib customizing legends http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 06 customizing legends ipynb learn about customizing plot legends in matplotlib customizing colorbars http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 07 customizing colorbars ipynb learn about customizing colorbars in matplotlib multiple subplots http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 08 multiple subplots ipynb learn about multiple subplots in matplotlib text and annotation http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 09 text and annotation ipynb learn about text and annotation in matplotlib customizing ticks http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 10 customizing ticks ipynb learn about customizing ticks in matplotlib settings and stylesheets http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 11 settings and stylesheets ipynb learn about customizing matplotlib configurations and stylesheets three dimensional plotting http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 12 three dimensional plotting ipynb learn about three dimensional plotting in matplotlib geographic data with basemap http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 13 geographic data with basemap ipynb learn about geographic data with basemap in matplotlib visualization with seaborn http nbviewer jupyter org github tarrysingh machine learning tutorials blob master matplotlib 04 14 visualization with seaborn ipynb learn about visualization with seaborn br p align center img src https raw githubusercontent com donnemartin data science ipython notebooks master images numpy png p numpy ipython notebook s demonstrating numpy functionality notebook description numpy http nbviewer ipython org github tarrysingh machine learning tutorials blob master numpy numpy ipynb adds python support for large multi dimensional arrays and matrices along with a large library of high level mathematical functions to operate on these arrays introduction to numpy http nbviewer jupyter org github tarrysingh machine learning tutorials blob master numpy 02 00 introduction to numpy ipynb introduction to numpy understanding data types http nbviewer jupyter org github tarrysingh machine learning tutorials blob master numpy 02 01 understanding data types ipynb learn about data types in python the basics of numpy arrays http nbviewer jupyter org github tarrysingh machine learning tutorials blob master numpy 02 02 the basics of numpy arrays ipynb learn about the basics of numpy arrays computation on arrays ufuncs http nbviewer jupyter org github tarrysingh machine learning tutorials blob master numpy 02 03 computation on arrays ufuncs ipynb learn about computations on numpy arrays universal functions computation on arrays aggregates http nbviewer jupyter org github tarrysingh machine learning tutorials blob master numpy 02 04 computation on arrays aggregates ipynb learn about aggregations min max and everything in between in numpy computation on arrays broadcasting http nbviewer jupyter org github tarrysingh machine learning tutorials blob master numpy 02 05 computation on arrays broadcasting ipynb learn about computation on arrays broadcasting in numpy boolean arrays and masks http nbviewer jupyter org github tarrysingh machine learning tutorials blob master numpy 02 06 boolean arrays and masks ipynb learn about comparisons masks and boolean logic in numpy fancy indexing http nbviewer jupyter org github tarrysingh machine learning tutorials blob master numpy 02 07 fancy indexing ipynb learn about fancy indexing in numpy sorting http nbviewer jupyter org github tarrysingh machine learning tutorials blob master numpy 02 08 sorting ipynb learn about sorting arrays in numpy structured data numpy http nbviewer jupyter org github tarrysingh machine learning tutorials blob master numpy 02 09 structured data numpy ipynb learn about structured data numpy s structured arrays br p align center img src https raw githubusercontent com donnemartin data science ipython notebooks master images python png p python data ipython notebook s demonstrating python functionality geared towards data analysis notebook description data structures http nbviewer ipython org github tarrysingh machine learning tutorials blob master python data structs ipynb learn python basics with tuples lists dicts sets data structure utilities http nbviewer ipython org github tarrysingh machine learning tutorials blob master python data structs utils ipynb learn python operations such as slice range xrange bisect sort sorted reversed enumerate zip list comprehensions functions http nbviewer ipython org github tarrysingh machine learning tutorials blob master python data functions ipynb learn about more advanced python features functions as objects lambda functions closures args kwargs currying generators generator expressions itertools datetime http nbviewer ipython org github tarrysingh machine learning tutorials blob master python data datetime ipynb learn how to work with python dates and times datetime strftime strptime timedelta logging http nbviewer ipython org github tarrysingh machine learning tutorials blob master python data logs ipynb learn about python logging with rotatingfilehandler and timedrotatingfilehandler pdb http nbviewer ipython org github tarrysingh machine learning tutorials blob master python data pdb ipynb learn how to debug in python with the interactive source code debugger unit tests http nbviewer ipython org github tarrysingh machine learning tutorials blob master python data unit tests ipynb learn how to test in python with nose unit tests br p align center img src https raw githubusercontent com donnemartin data science ipython notebooks master images kaggle png p kaggle and business analyses ipython notebook s used in kaggle https www kaggle com competitions and business analyses notebook description titanic http nbviewer ipython org github tarrysingh machine learning tutorials blob master kaggle titanic ipynb predict survival on the titanic learn data cleaning exploratory data analysis and machine learning churn analysis http nbviewer ipython org github tarrysingh machine learning tutorials blob master analyses churn ipynb predict customer churn exercise logistic regression gradient boosting classifers support vector machines random forests and k nearest neighbors includes discussions of confusion matrices roc plots feature importances prediction probabilities and calibration descrimination br p align center img src https raw githubusercontent com donnemartin data science ipython notebooks master images spark png p spark ipython notebook s demonstrating spark and hdfs functionality notebook description spark http nbviewer ipython org github tarrysingh machine learning tutorials blob master spark spark ipynb in memory cluster computing framework up to 100 times faster for certain applications and is well suited for machine learning algorithms hdfs http nbviewer ipython org github tarrysingh machine learning tutorials blob master spark hdfs ipynb reliably stores very large files across machines in a large cluster br p align center img src https raw githubusercontent com donnemartin data science ipython notebooks master images mrjob png p mapreduce python ipython notebook s demonstrating hadoop mapreduce with mrjob functionality notebook description mapreduce python http nbviewer ipython org github tarrysingh machine learning tutorials blob master mapreduce mapreduce python ipynb runs mapreduce jobs in python executing jobs locally or on hadoop clusters demonstrates hadoop streaming in python code with unit test and mrjob https github com yelp mrjob config file to analyze amazon s3 bucket logs on elastic mapreduce disco https github com discoproject disco is another python based alternative br p align center img src https raw githubusercontent com donnemartin data science ipython notebooks master images aws png p aws ipython notebook s demonstrating amazon web services aws and aws tools functionality also check out saws https github com donnemartin saws a supercharged aws command line interface cli awesome aws https github com donnemartin awesome aws a curated list of libraries open source repos guides blogs and other resources notebook description boto http nbviewer ipython org github tarrysingh machine learning tutorials blob master aws aws ipynb boto official aws sdk for python s3cmd http nbviewer ipython org github tarrysingh machine learning tutorials blob master aws aws ipynb s3cmd interacts with s3 through the command line s3distcp http nbviewer ipython org github tarrysingh machine learning tutorials blob master aws aws ipynb s3distcp combines smaller files and aggregates them together by taking in a pattern and target file s3distcp can also be used to transfer large volumes of data from s3 to your hadoop cluster s3 parallel put http nbviewer ipython org github tarrysingh machine learning tutorials blob master aws aws ipynb s3 parallel put uploads multiple files to s3 in parallel redshift http nbviewer ipython org github tarrysingh machine learning tutorials blob master aws aws ipynb redshift acts as a fast data warehouse built on top of technology from massive parallel processing mpp kinesis http nbviewer ipython org github tarrysingh machine learning tutorials blob master aws aws ipynb kinesis streams data in real time with the ability to process thousands of data streams per second lambda http nbviewer ipython org github tarrysingh machine learning tutorials blob master aws aws ipynb lambda runs code in response to events automatically managing compute resources br p align center img src https raw githubusercontent com donnemartin data science ipython notebooks master images commands png p commands ipython notebook s demonstrating various command lines for linux git etc notebook description linux http nbviewer ipython org github tarrysingh machine learning tutorials blob master commands linux ipynb unix like and mostly posix compliant computer operating system disk usage splitting files grep sed curl viewing running processes terminal syntax highlighting and vim anaconda http nbviewer ipython org github tarrysingh machine learning tutorials blob master commands misc ipynb anaconda distribution of the python programming language for large scale data processing predictive analytics and scientific computing that aims to simplify package management and deployment ipython notebook http nbviewer ipython org github tarrysingh machine learning tutorials blob master commands misc ipynb ipython notebook web based interactive computational environment where you can combine code execution text mathematics plots and rich media into a single document git http nbviewer ipython org github tarrysingh machine learning tutorials blob master commands misc ipynb git distributed revision control system with an emphasis on speed data integrity and support for distributed non linear workflows ruby http nbviewer ipython org github tarrysingh machine learning tutorials blob master commands misc ipynb ruby used to interact with the aws command line and for jekyll a blog framework that can be hosted on github pages jekyll http nbviewer ipython org github tarrysingh machine learning tutorials blob master commands misc ipynb jekyll simple blog aware static site generator for personal project or organization sites renders markdown or textile and liquid templates and produces a complete static website ready to be served by apache http server nginx or another web server pelican http nbviewer ipython org github tarrysingh machine learning tutorials blob master commands misc ipynb pelican python based alternative to jekyll django http nbviewer ipython org github tarrysingh machine learning tutorials blob master commands misc ipynb django high level python web framework that encourages rapid development and clean pragmatic design it can be useful to share reports analyses and for blogging lighter weight alternatives include pyramid https github com pylons pyramid flask https github com pallets flask tornado https github com tornadoweb tornado and bottle https github com bottlepy bottle misc ipython notebook s demonstrating miscellaneous functionality notebook description regex http nbviewer ipython org github tarrysingh machine learning tutorials blob master misc regex ipynb regular expression cheat sheet useful in data wrangling algorithmia http nbviewer ipython org github tarrysingh machine learning tutorials blob master misc algorithmia ipynb algorithmia is a marketplace for algorithms this notebook showcases 4 different algorithms face detection content summarizer latent dirichlet allocation and optical character recognition notebook installation anaconda anaconda is a free distribution of the python programming language for large scale data processing predictive analytics and scientific computing that aims to simplify package management and deployment follow instructions to install anaconda https docs continuum io anaconda install or the more lightweight miniconda http conda pydata org miniconda html dev setup for detailed instructions scripts and tools to set up your development environment for data analysis check out the dev setup https github com donnemartin dev setup repo running notebooks note if you intend to learn the hard way preferred method then i d strongly advice to write as much code as you can yourself and not just run pre written code if you still want to test it then do the following to view interactive content or to modify elements within the ipython notebooks you must first clone or download the repository then run the notebook more information on ipython notebooks can be found here http ipython org notebook html git clone https github com tarrysingh artificial intelligence deep learning machine learning tutorials git cd artificial intelligence deep learning machine learning tutorials jupyter notebook notebooks tested with python 3 7 curated list of deeplearning blogs a blog from a human engineer being http www erogol com rss http www erogol com feed aakash japi http aakashjapi com rss http logicx24 github io feed xml adit deshpande https adeshpande3 github io rss https adeshpande3 github io adeshpande3 github io feed xml advanced analytics r http advanceddataanalytics net rss http advanceddataanalytics net feed adventures in data land http blog smola org rss http blog smola org rss agile data science http blog sense io rss http blog sense io rss ahmed el deeb https medium com d33b rss https medium com feed d33b airbnb data blog http nerds airbnb com data rss http nerds airbnb com feed alex castrounis innoarchitech http www innoarchitech com rss http www innoarchitech com feed xml alex perrier http alexperrier github io rss http alexperrier github io feed xml algobeans data analytics tutorials experiments for the layman https algobeans com rss https algobeans com feed amazon aws ai blog https aws amazon com blogs ai rss https aws amazon com blogs amazon ai feed analytics vidhya http www analyticsvidhya com blog rss http feeds feedburner com analyticsvidhya analytics and visualization in big data sicara https blog sicara com rss https blog sicara com feed andreas m ller http peekaboo vision blogspot com rss http peekaboo vision blogspot com atom xml andrej karpathy blog http karpathy github io rss http karpathy github io feed xml andrew brooks http brooksandrew github io simpleblog rss http brooksandrew github io simpleblog feed xml andrey kurenkov http www andreykurenkov com writing rss http www andreykurenkov com writing feed xml anton lebedevich s blog http mabrek github io rss http mabrek github io feed xml arthur juliani https medium com awjuliani rss https medium com feed awjuliani audun m ygard http www auduno com rss http auduno tumblr com rss avi singh https avisingh599 github io rss http avisingh599 github io feed xml beautiful data http beautifuldata net rss http beautifuldata net feed beckerfuffle http mdbecker github io rss http mdbecker github io atom xml becoming a data scientist http www becomingadatascientist com rss http www becomingadatascientist com feed ben bolte s blog http benjaminbolte com ml rss http benjaminbolte com ml ben frederickson http www benfrederickson com blog rss http www benfrederickson com atom xml berkeley ai research http bair berkeley edu blog rss http bair berkeley edu blog feed xml big ish data http bigishdata com rss http bigishdata com feed blog on neural networks http yerevann github io rss http yerevann github io atom xml blogistic regressionabout projects http d10genes github io blog rss http d10genes github io blog feed xml blogr r tips and tricks from a scientist https drsimonj svbtle com rss https drsimonj svbtle com brain of mat kelcey http matpalm com blog rss http matpalm com blog feed brilliantly wrong thoughts on science and programming https arogozhnikov github io rss http arogozhnikov github io feed xml bugra akyildiz http bugra github io rss http bugra github io feeds all atom xml building babylon https building babylon net rss http building babylon net feed carl shan http carlshan com rss http feeds feedburner com carlshan chris stucchio https www chrisstucchio com blog index html rss http www chrisstucchio com blog atom xml christophe bourguignat https medium com chris bour rss https medium com feed chris bour christopher nguyen https medium com ctn rss https medium com feed ctn cloudera data science posts http blog cloudera com blog category data science rss http blog cloudera com blog category data science feed colah s blog http colah github io archive html rss http colah github io rss xml cortana intelligence and machine learning blog https blogs technet microsoft com machinelearning rss http blogs technet com b machinelearning rss aspx daniel forsyth http www danielforsyth me rss http www danielforsyth me rss daniel homola http danielhomola com category blog rss http danielhomola com feed daniel nee http danielnee com rss http danielnee com feed rss2 data based inventions http datalab lu rss http datalab lu atom xml data blogger https www data blogger com rss https www data blogger com feed data labs http blog insightdatalabs com rss http blog insightdatalabs com rss data meets media http datameetsmedia com rss http datameetsmedia com feed data miners blog http blog data miners com rss http blog data miners com feeds posts default alt rss data mining research http www dataminingblog com rss http feeds feedburner com dataminingblog data mining text mining visualization and social media http datamining typepad com data mining rss http datamining typepad com data mining atom xml data piques http blog ethanrosenthal com rss http blog ethanrosenthal com feeds all atom xml data school http www dataschool io rss http www dataschool io rss data science 101 http 101 datascience community rss http 101 datascience community feed data science facebook https research facebook com blog datascience rss https research facebook com blog datascience data science insights http www datasciencebowl com data science insights rss http www datasciencebowl com feed data science tutorials https codementor io data science tutorial rss https www codementor io data science tutorial feed data science vademecum http datasciencevademecum wordpress com rss http datasciencevademecum wordpress com feed dataaspirant http dataaspirant com rss http dataaspirant wordpress com feed dataclysm http blog okcupid com rss http blog okcupid com index php feed datagenetics http datagenetics com blog html rss http datagenetics com feed rss xml dataiku https www dataiku com blog rss http www dataiku com feed xml datakind http www datakind org blog rss http feeds feedburner com datakin datalook http blog datalook io rss http blog datalook io feed datanice https datanice wordpress com rss https datanice wordpress com feed dataquest blog https www dataquest io blog rss https www dataquest io blog atom xml datarobot http www datarobot com blog rss http www datarobot com feed datascope http datascopeanalytics com blog rss http datascopeanalytics com rss datasframe http tomaugspurger github io rss http tomaugspurger github io feeds all rss xml david mimno http www mimno org rss http mimno infosci cornell edu b feed xml dayne batten http daynebatten com rss http daynebatten com feed deep learning http deeplearning net blog rss http deeplearning net feed deepdish http deepdish io rss http deepdish io atom xml delip rao http deliprao com rss http deliprao com feed denny s blog http blog dennybritz com rss http blog dennybritz com feed dimensionless https dimensionless in blog rss https dimensionless in feed distill http distill pub rss http distill pub rss xml district data labs http districtdatalabs silvrback com rss https districtdatalabs silvrback com feed diving into data https blog datadive net rss http blog datadive net feed domino data lab s blog http blog dominodatalab com rss http blog dominodatalab com rss dr randal s olson http www randalolson com blog rss http www randalolson com feed drew conway https medium com drewconway rss https medium com feed drewconway dustin tran http dustintran com blog rss http dustintran com blog rss eder santana https edersantana github io blog html rss http edersantana github io feed xml edwin chen http blog echen me rss http blog echen me feeds all rss xml efavdb http efavdb com rss http efavdb com feed emilio ferrara ph d http www emilio ferrara name rss http www emilio ferrara name feed entrepreneurial geekiness http ianozsvald com rss http ianozsvald com feed eric jonas http ericjonas com archives html rss http ericjonas com archives html eric siegel http www predictiveanalyticsworld com blog rss http feeds feedburner com predictiveanalyticsworld gxry erik bern http erikbern com rss http erikbern com feed erin shellman http www erinshellman com rss http www erinshellman com feed eugenio culurciello http culurciello github io rss http culurciello github io feed xml fabian pedregosa http fa bianp net rss http fa bianp net blog feed fast forward labs http blog fastforwardlabs com rss http blog fastforwardlabs com rss fastml http fastml com rss http fastml com atom xml florian hartl http florianhartl com rss http florianhartl com feed flowingdata http flowingdata com rss http flowingdata com feed full stack ml http fullstackml com rss http fullstackml com feed gab41 http www lab41 org gab41 rss http www lab41 org feed garbled notes http www chioka in rss http www chioka in feed xml greg reda http www gregreda com blog rss http www gregreda com feeds all atom xml hyon s chu https medium com adailyventure rss https medium com feed adailyventure i am trask http iamtrask github io rss http iamtrask github io feed xml i quant ny http iquantny tumblr com rss http iquantny tumblr com rss inference http www inference vc rss http www inference vc rss insight data science https blog insightdatascience com rss https blog insightdatascience com feed inspiration information http myinspirationinformation com rss http myinspirationinformation com feed ira korshunova http irakorshunova github io rss http irakorshunova github io feed xml i m a bandit https blogs princeton edu imabandit rss https blogs princeton edu imabandit feed jason toy http www jtoy net rss http jtoy net atom xml jeremy d jackson phd http www jeremydjacksonphd com rss http www jeremydjacksonphd com feed rss2 jesse steinweg woods https jessesw com rss https jessesw com feed xml joe cauteruccio http www joecjr com rss http www joecjr com feed john myles white http www johnmyleswhite com rss http www johnmyleswhite com feed john s soapbox http joschu github io rss http joschu github io feed xml jonas degrave http 317070 github io rss http 317070 github io feed xml joy of data http www joyofdata de blog rss http www joyofdata de blog feed julia evans http jvns ca rss http jvns ca atom xml kdnuggets http www kdnuggets com rss http feeds feedburner com kdnuggets data mining analytics keeping up with the latest techniques http colinpriest com rss http colinpriest com feed kenny bastani http www kennybastani com rss http www kennybastani com feeds posts default alt rss kevin davenport http kldavenport com rss http kldavenport com feed kevin frans http kvfrans com rss http kvfrans com rss korbonits math data http korbonits github io rss http korbonits github io feed xml large scale machine learning http bickson blogspot com rss http bickson blogspot com feeds posts default lateral blog https blog lateral io rss https blog lateral io feed lazy programmer http lazyprogrammer me rss http lazyprogrammer me feed learn analytics here https learnanalyticshere wordpress com rss https learnanalyticshere wordpress com feed learndatasci http www learndatasci com rss http www learndatasci com feed learning with data http learningwithdata com rss http learningwithdata com rss feed xml life language learning http daoudclarke github io rss http daoudclarke github io atom xml locke data https itsalocke com blog rss https itsalocke com feed louis dorard http www louisdorard com blog rss http www louisdorard com blog format rss m e driscoll http medriscoll com rss http medriscoll com rss machinalis http www machinalis com blog rss http www machinalis com blog feeds rss machine learning theory http hunch net rss http hunch net feed rss2 machine learning and data science http alexhwoods com blog rss http alexhwoods com feed machine learning https charlesmartin14 wordpress com rss http charlesmartin14 wordpress com feed machine learning mastery http machinelearningmastery com blog rss http machinelearningmastery com feed machine learning blogs https machinelearningblogs com rss https machinelearningblogs com feed machine learning etc http yaroslavvb blogspot com rss http yaroslavvb blogspot com feeds posts default machine learning maths and physics https mlopezm wordpress com rss https mlopezm wordpress com feed machine learning flashcards https machinelearningflashcards com 10 but a nicely illustrated set of 300 flash cards machined learnings http www machinedlearnings com rss http www machinedlearnings com feeds posts default mapping babel https jack clark net rss https jack clark net feed mapr blog https www mapr com blog rss https www mapr com bigdata xml marek rei http www marekrei com blog rss http www marekrei com blog feed marginally interesting http blog mikiobraun de rss http feeds feedburner com marginallyinteresting math programming http jeremykun com rss http jeremykun wordpress com feed matthew rocklin http matthewrocklin com blog rss http matthewrocklin com blog atom xml melody wolk http melodywolk com projects rss http melodywolk com feed mic farris http www micfarris com rss http www micfarris com feed mike tyka http mtyka github io rss http mtyka github io feed xml minimaxir max woolf s blog http minimaxir com rss http minimaxir com rss xml mirror image https mirror2image wordpress com rss http mirror2image wordpress com feed mitch crowe http www dataphoric com rss http www dataphoric com feed xml mlwave http mlwave com rss http mlwave com feed mlwhiz http mlwhiz com rss http mlwhiz com atom xml models are illuminating and wrong https peadarcoyle wordpress com rss http peadarcoyle wordpress com feed moody rd http blog mrtz org rss http blog mrtz org feed xml moonshots http jxieeducation com rss http jxieeducation com feed xml mourad mourafiq http mourafiq com rss http mourafiq com atom xml my thoughts on data science predictive analytics python http shahramabyari com rss http shahramabyari com feed natural language processing blog http nlpers blogspot fr rss http nlpers blogspot com feeds posts default neil lawrence http inverseprobability com blog html rss http inverseprobability com rss xml nlp and deep learning enthusiast http camron xyz rss http camron xyz index php feed no free hunch http blog kaggle com rss http blog kaggle com feed nuit blanche http nuit blanche blogspot com rss http nuit blanche blogspot com feeds posts default number 2147483647 https no2147483647 wordpress com rss http no2147483647 wordpress com feed on machine intelligence https aimatters wordpress com rss https aimatters wordpress com feed opiate for the masses data is our religion http opiateforthemass es rss http opiateforthemass es feed xml p value info http www p value info rss http www p value info feeds posts default pete warden s blog http petewarden com rss http feeds feedburner com typepad petewarden plotly blog http blog plot ly rss http blog plot ly rss probably overthinking it http allendowney blogspot ca rss http allendowney blogspot com feeds posts default prooffreader com http www prooffreader com rss http www prooffreader com feeds posts default prooffreaderplus http prooffreaderplus blogspot ca rss http prooffreaderplus blogspot ca feeds posts default publishable stuff http www sumsar net rss http www sumsar net atom xml pyimagesearch http www pyimagesearch com rss http feeds feedburner com pyimagesearch pythonic perambulations https jakevdp github io rss http jakevdp github com atom xml quintuitive http quintuitive com rss http quintuitive com feed r and data mining https rdatamining wordpress com rss http rdatamining wordpress com feed r bloggers http www r bloggers com rss http feeds feedburner com rbloggers r2rt http r2rt com rss http r2rt com feeds all atom xml ramiro g mez http ramiro org notebooks rss http ramiro org notebook rss xml random notes on computer science mathematics and software engineering http barmaley exe github io rss http feeds feedburner com barmaley exe blog feed randy zwitch http randyzwitch com rss http randyzwitch com feed xml rare technologies http rare technologies com blog rss http rare technologies com feed rayli net http rayli net blog rss http rayli net blog feed revolutions http blog revolutionanalytics com rss http blog revolutionanalytics com atom xml rinu boney http rinuboney github io rss http rinuboney github io feed xml rnduja blog http rnduja github io rss http rnduja github io feed xml robert chang https medium com rchang rss https medium com feed rchang rocket powered data science http rocketdatascience org rss http rocketdatascience org feed rss2 sachin joglekar s blog https codesachin wordpress com rss https codesachin wordpress com feed samim https medium com samim rss https medium com feed samim sean j taylor http seanjtaylor com rss http seanjtaylor com rss sebastian raschka http sebastianraschka com blog index html rss http sebastianraschka com rss feed xml sebastian ruder http sebastianruder com rss http sebastianruder com rss sebastian s slow blog http www nowozin net sebastian blog rss http www nowozin net sebastian blog feeds all atom xml sfl scientific blog https sflscientific com blog rss http sflscientific com blog format rss shakir s machine learning blog http blog shakirm com rss http blog shakirm com feed simply statistics http simplystatistics org rss http simplystatistics org feed springboard blog http springboard com blog startup ml blog http startup ml blog rss http www startup ml blog format rss statistical modeling causal inference and social science http andrewgelman com rss http andrewgelman com feed stigler diet http stiglerdiet com rss http stiglerdiet com feeds all atom xml stitch fix tech blog http multithreaded stitchfix com blog rss http multithreaded stitchfix com feed xml stochastic r d notes http arseny info rss http arseny info feeds all rss xml storytelling with statistics on quora http datastories quora com rss http datastories quora com rss streamhacker http streamhacker com rss http feeds feedburner com streamhacker subconscious musings http blogs sas com content subconsciousmusings rss http feeds feedburner com advanalytics swan intelligence http swanintelligence com rss http swanintelligence com feeds all rss xml technocalifornia http technocalifornia blogspot se rss http technocalifornia blogspot com feeds posts default text analysis blog aylien http blog aylien com rss http blog aylien com rss the angry statistician http angrystatistician blogspot com rss http angrystatistician blogspot com feeds posts default the clever machine https theclevermachine wordpress com rss http theclevermachine wordpress com feed the data camp blog https www datacamp com community blog rss http blog datacamp com feed the data incubator http blog thedataincubator com rss http blog thedataincubator com feed the data science lab https datasciencelab wordpress com rss http datasciencelab wordpress com feed the etz files http alexanderetz com rss http nicebrain wordpress com feed the science of data http www martingoodson com rss http www martingoodson com rss the shape of data https shapeofdata wordpress com rss https shapeofdata wordpress com feed the unofficial google data science blog http www unofficialgoogledatascience com rss http www unofficialgoogledatascience com feeds posts default tim dettmers http timdettmers com rss http timdettmers com feed tombone s computer vision blog http www computervisionblog com rss http www computervisionblog com feeds posts default tommy blanchard http tommyblanchard com category projects rss http tommyblanchard com feeds all atom xml trevor stephens http trevorstephens com rss http trevorstephens com feed xml trey causey http treycausey com rss http treycausey com feeds all atom xml uw data science blog http datasciencedegree wisconsin edu blog rss http datasciencedegree wisconsin edu feed wellecks http wellecks wordpress com rss http wellecks wordpress com feed wes mckinney http wesmckinney com archives html rss http wesmckinney com feeds all atom xml while my mcmc gently samples http twiecki github io rss http twiecki github io atom xml wildml http www wildml com rss http www wildml com feed will do stuff for stuff http rinzewind org blog en rss http rinzewind org feed en will wolf http willwolf io rss http willwolf io feed will s noise http www willmcginnis com rss http www willmcginnis com feed william lyon http www lyonwj com rss http www lyonwj com atom xml win vector blog http www win vector com blog rss http www win vector com blog feed yanir seroussi http yanirseroussi com rss http yanirseroussi com feed zac stewart http zacstewart com rss http zacstewart com feed xml hat http blog yhat com rss http blog yhat com rss xml uantitative ourney http outlace com rss http outlace com feed xml http blog otoro net rss http blog otoro net feed xml credits python for data analysis data wrangling with pandas numpy and ipython http www amazon com python data analysis wrangling ipython dp 1449319793 by wes mckinney pycon 2015 scikit learn tutorial https github com jakevdp sklearn pycon2015 by jake vanderplas python data science handbook https github com jakevdp pythondatasciencehandbook by jake vanderplas parallel machine learning with scikit learn and ipython https github com ogrisel parallel ml tutorial by olivier grisel statistical interference using computational methods in python https github com allendowney compstats by allen downey tensorflow examples https github com aymericdamien tensorflow examples by aymeric damien tensorflow tutorials https github com pkmital tensorflow tutorials by parag k mital tensorflow tutorials https github com nlintz tensorflow tutorials by nathan lintz tensorflow tutorials https github com alrojo tensorflow tutorial by alexander r johansen tensorflow book https github com binroot tensorflow book by nishant shukla summer school 2015 https github com mila udem summerschool2015 by mila udem keras tutorials https github com leriomaggio deep learning keras tensorflow by valerio maggio kaggle https www kaggle com yhat blog http blog yhat com contributing contributions are welcome for bug reports or requests please submit an issue https github com tarrysingh machine learning tutorials issues contact info feel free to contact me to discuss any issues questions or comments email tarry singh gmail com mailto tarry singh gmail com twitter tarrysingh https twitter com tarrysingh github tarrysingh https github com tarrysingh com linkedin tarry singh https www linkedin com in tarrysingh website tarrysingh com https tarrysingh com medium tarry medium https medium com tarrysingh quora answers from tarry on quora https www quora com profile tarry singh license this repository contains a variety of content some developed by tarry singh and some from third parties and a lot will be maintained by me the third party content is distributed under the license provided by those parties the content was originally started by donne martin is distributed under the following license in 2017 i have been further developing and maintaining it by adding pytorch torch lua mxnet and much more i am providing code and resources in this repository to you under an open source license copyright 2017 tarry singh licensed under the apache license version 2 0 the license you may not use this file except in compliance with the license you may obtain a copy of the license at http www apache org licenses license 2 0 unless required by applicable law or agreed to in writing software distributed under the license is distributed on an as is basis without warranties or conditions of any kind either express or implied see the license for the specific language governing permissions and limitations under the license | machine-learning deep-learning tensorflow python pytorch keras lua matplotlib aws kaggle pandas scikit-learn torch artificial-intelligence neural-network convolutional-neural-networks tensorflow-tutorials python-data ipython-notebook capsule-network | ai |
frontend-tools | front end development tools mostly english readme zh cn md table of contents a name toc a tools catalog search discovery comparison service tool search ecmascript javascript ecmascript specification es specification support compatibility es support documentation guide es doc javascript runtime js runtime javascript variant compiler transpiler js variant javascript framework js framework javascript ui view library framework js ui library react based library framework platform react library vue based library framework vue library front end css framework frontend framework small css library toolkit small css library shim polyfill shim web development web dev mobile development mobile dev desktop development desktop dev data model state management library state management redux based library redux library database database internationalization i18n localization l10n i18n javascript utility library js utility library javascript module system and loader loader module and asset bundler bundler package manager package manager css processor css processor css tool css tool linting validation checklist linting testing testing debug debug documentation documentation code processing code processing minification mini unminifier unmini task runner build tool task runner automation automation boilerplate scaffolding boilerplate component development component dev design design graphics image editor image editor images icons images analysis performance optimization analysis technologies support tech support network net version control version control git git development server dev server node js based dev server node with php support dev server php node js version management node manage editor ide editor playground interactive computing playground online development playground online dev online tool online tool site generator site generator emulator simulator emulator api api browser extension browser extension benchmark benchmark hosting cloud services hosting code cdn code cdn guide reference practices recipes guide css css guide html html guide javascript js guide typescript ts guide books books examples examples css css examples html html examples news digest news useful articles resources resources tools catalog search discovery comparison service a name tool search a x2191 nbsp x2191 nbsp x2191 toc alternativeto https alternativeto net a free service that helps you find better alternatives to the products you love and hate awesome https awesome re a curated list of awesome lists awesome open source https awesomeopensource com find open source by searching browsing and combining topics awesome react components https github com brillout awesome react components curated list of react components libraries best of javascript https bestofjs org a place to find the best components to build amazing web applications css script https www cssscript com a javascript css code library aims to provide the newest best and free css javascript resources for web mobile developers and designers free for developers https free for dev a list of software saas paas iaas etc and other offerings that have free tiers for developers headlesscms org https headlesscms org a list of content management systems for jamstack sites ireact http ireact cn helps you discover the most fantastic powerful react components and libraries and makes it easy for you to pick one that ll work for you javascripting https www javascripting com the definitive source of the best javascript libraries frameworks and plugins jquery plugins https jquery plugins net categorized collection of jquery plugins jqueryscript net https www jqueryscript net one of jquery plugin websites that provide web designers and developers with a simple way to preview and download a variety of free jquery plugins jster http jster net a catalog of frontend javascript libraries js coach https js coach an opinionated catalog of open source js packages libhunt https www libhunt com our goal is to help you find the software and libraries you need all lists have been crafted by many experts from the relevant github communities libraries io https libraries io helps developers find new open source libraries modules and frameworks and keep track of ones they depend upon microjs http microjs com fantastic micro frameworks and micro libraries for fun and profit moiva https moiva io measure and compare javascript libraries node frameworks http nodeframework com hand picked registry of node js frameworks node js toolbox https nodejstoolbox com find actively maintained and popular libraries in the node js ecosystem npmcompare https npmcompare com search and compare npm packages npms https npms io a better and open source search for node modules npm trends https www npmtrends com compare package download counts over time pika https www pika dev search npm for fast modern packages redux ecosystem links https github com markerikson redux ecosystem links a categorized list of addon libraries for redux as well as other libraries that are closely related slant https www slant co a product recommendation community that helps connect people with the best products for them stackshare https stackshare io discover discuss the best software tools services staticgen com https www staticgen com a leaderboard of top open source static site generators unheap http www unheap com a tidy repository of javascript plugins vuescript com https www vuescript com aims to offer latest free vue js components for web application developers webcomponents org https www webcomponents org a place to publish browse and search for reusable web ui components ecmascript javascript a name ecmascript a x2191 nbsp x2191 nbsp x2191 toc specification a name es specification a ecmascript standard specifications http www ecma international org publications standards ecma 262 arch htm version 3 pdf http www ecma international org publications files ecma st arch ecma 262 203rd 20edition 20december 201999 pdf version 5 1 html http www ecma international org ecma 262 5 1 index html pdf http www ecma international org publications files ecma st arch ecma 262 205 1 20edition 20june 202011 pdf version 6 2015 html http www ecma international org ecma 262 6 0 index html pdf http www ecma international org publications files ecma st arch ecma 262 206th 20edition 20june 202015 pdf version 8 2017 html https www ecma international org ecma 262 8 0 index html pdf https www ecma international org publications files ecma st ecma 262 pdf tc39 proposals https prop tc39 now sh support compatibility a name es support a ecmascript compatibility tables https kangax github io compat table node green http node green node js ecmascript compatibility tables documentation guide a name es doc a es6features https github com lukehoban es6features overview of ecmascript 6 features exploring js http exploringjs com javascript books for programmers javascript runtime a name js runtime a x2191 nbsp x2191 nbsp x2191 toc deno https deno land a javascript typescript runtime with secure defaults and a great developer experience node js https nodejs org an asynchronous event driven javascript runtime designed to build scalable network applications ringo https ringojs org a javascript platform built on the jvm and optimized for server side applications javascript variant compiler transpiler a name js variant a x2191 nbsp x2191 nbsp x2191 toc babel https babeljs io a javascript compiler bubl https buble surge sh fast batteries included es2015 compiler sucrase https sucrase io super fast alternative to babel for when you can target modern js runtimes swc https swc rs a typescript javascript compiler it takes javascript typescript files using modern javascript features and outputs valid code that is supported by all major browsers typescript http www typescriptlang org a typed superset of javascript that compiles to plain javascript javascript framework a name js framework a x2191 nbsp x2191 nbsp x2191 toc angular 2 https angular io a development platform for building mobile and desktop web applications aurelia http aurelia io a javascript client framework for mobile desktop and web leveraging simple conventions and empowering creativity choo https github com yoshuawuyts choo framework for creating sturdy frontend applications cyclow http cyclow js org a reactive frontend framework ember http emberjs com a framework for creating ambitious web applications hyperapp https github com hyperapp hyperapp a javascript library for building frontend applications mithril https mithril js org a modern client side javascript framework for building single page applications qooxdoo http www qooxdoo org a universal javascript framework that enables you to create applications for a wide range of platforms javascript ui view library framework a name js ui library a x2191 nbsp x2191 nbsp x2191 toc alpine js https github com alpinejs alpine a rugged minimal framework for composing javascript behavior in your markup alpine js offers you the reactive and declarative nature of big frameworks like vue or react at a much lower cost cell https www celljs org a self constructing web app framework powered by a self driving dom inferno https infernojs org an extremely fast react like javascript library for building modern user interfaces marko https markojs com a friendly and fast ui library that makes building web apps fun melody https melody js org a fast and memory efficient library for creating highly dynamic user interfaces monkberry https monkberry js org blazingly fast small and simple javascript library for building web user interfaces moon https moonjs org the minimal fast library for functional user interfaces nerv https github com nervjs nerv a blazing fast react alternative compatible with ie8 and react 16 preact https preactjs com fast 3kb alternative to react with the same es6 api ractive js https ractive js org a javascript library for building reactive user interfaces in a way that doesn t force you into a particular framework s way of thinking react https reactjs org a javascript library for building user interfaces riot https riot js org simple and elegant component based ui library solid https github com ryansolid solid a declarative efficient and flexible javascript library for building user interfaces svelte https svelte dev rather than interpreting your application code at run time your app is converted into ideal javascript at build time vue js https vuejs org simple yet powerful library for building modern web interfaces react based library framework platform a name react library a x2191 nbsp x2191 nbsp x2191 toc ant design https ant design docs react introduce an enterprise class ui design language and react based implementation blueprint https blueprintjs com a react based ui toolkit for the web it is optimized for building complex data dense web interfaces for desktop applications chakra ui https chakra ui com a simple modular and accessible component library that gives you all the building blocks you need to build your react applications dva https github com dvajs dva react and redux based lightweight and elm style framework electrode http www electrode io a platform for building universal react node js applications with standardized structure best practices and modern technologies baked in elemental ui http elemental ui com a ui toolkit for react js websites and apps fusion js https fusionjs com modern framework for fast powerful react apps fusion js is a universal web framework that represents the fusion of the client and the server it s geared for server side rendering out of the box and its plugin driven architecture allows for complex frontend and backend logic to be encapsulated in a single plugin grommet https grommet io a react based framework that provides accessibility modularity responsiveness and theming in a tidy package libreact https github com streamich libreact a collection of most essential react utilities you will probably need in any project material ui https material ui com a set of react components that implement google s material design react md https react md dev an accessible react component library built from the material design guidelines in sass react toolbox http react toolbox io a set of react components that implements google material design specification reactxp https microsoft github io reactxp a library for cross platform app development using react and react native rebass https rebassjs org react primitive ui components built with styled system vue based library framework a name vue library a x2191 nbsp x2191 nbsp x2191 toc balmui https material balmjs com next generation material ui for vue js buefy https buefy org a lightweight library of responsive ui components for vue js based on bulma framework and design element http element eleme io a vue js 2 0 ui toolkit for web iview https www iviewui com a high quality ui toolkit built on vue js keen ui https josephuspaye github io keen ui a lightweight collection of essential ui components written with vue js and inspired by material design muse ui https museui github io a vue 2 0 and material design based ui component library quasar framework https quasar dev build high performance vuejs user interfaces in record time vuetify js https vuetifyjs com a component framework for vue js 2 vue material https vuematerial io simple lightweight and built exactly according to the google material design specs build well designed apps that can fit on every screen with support to all modern web browsers with dynamic themes components on demand and all with an ease to use api front end css framework a name frontend framework a x2191 nbsp x2191 nbsp x2191 toc agnosticui https www agnosticui com a ui component library designed to work with multiple javascript frameworks react vue svelte and angular blaze https www blazeui com an open source modular toolkit it provides great structure for building websites quickly with a scalable and maintainable foundation bootflat http bootflat github io an open source flat ui kit based on bootstrap 3 3 0 css framework bootstrap https getbootstrap com an open source toolkit for developing with html css and js bulma https bulma io a modern css framework based on flexbox flat ui http designmodo github io flat ui a beautiful theme for bootstrap foundation https get foundation the most advanced responsive front end framework in the world froala design blocks https www froala com design blocks a set of 170 bootstrap based design blocks ready to be used to create clean modern websites groundworkcss http groundworkcss github io outdated a fully responsive html5 css and javascript toolkit halfmoon https www gethalfmoon com front end framework with a built in dark mode and full customizability using css variables great for building dashboards and tools ink http ink sapo pt an interface kit for quick development of web interfaces simple to use and expand on inuitcss https github com inuitcss inuitcss extensible scalable sass based oocss framework for large and long lasting ui projects it does not provide you with ui and design out of the box instead it provides you with a solid architectural baseline upon which to complete your own work kube https imperavi com kube clean minimalistic and fast to implement css js framework for professional developers and designers alike material components for the web https github com material components material components web modular and customizable material design ui components for the web developed by a core team of engineers and ux designers at google these components enable a reliable development workflow to build beautiful and functional web projects material design lite https getmdl io lets you add a material design look and feel to your websites it doesn t rely on any javascript frameworks and aims to optimize for cross device use gracefully degrade in older browsers and offer an experience that is immediately accessible material framework http nt1m github io material framework a simple responsive css framework that allows you to integrate material design in any web page or web app materialize https materializecss com a modern responsive front end framework based on material design metro ui https metroui org ua sleek intuitive and powerful front end framework for faster and easier web development build responsive mobile first projects on the web with the first front end component library in metro style polymer https www polymer project org libraries tools and patterns to help developers build modern progressive web apps taking full advantage of cutting edge platform features like web components service workers and http 2 semantic ui https semantic ui com a development framework that helps create beautiful responsive layouts using human friendly html shorthand https shorthandcss bansal io a free and open source css framework that allows you to make unique and modern design without writing any css spectre css https picturepan2 github io spectre a lightweight responsive and modern css framework tailwind css https tailwindcss com a utility first css framework for rapid ui development topcoat http topcoat io css for clean and fast web apps turret https turretcss com a styles and browser behaviour normalisation framework for rapid development of responsive and accessible websites uikit https getuikit com a lightweight and modular front end framework for developing fast and powerful web interfaces small css library toolkit a name small css library a x2191 nbsp x2191 nbsp x2191 toc basscss https basscss com low level css toolkit a lightweight collection of immutable utilities designed for speed clarity performance and scalability cutestrap https www cutestrap com a sassy opinionated css framework a tiny alternative to bootstrap mini css https minicss us a minimal responsive style agnostic css framework mobi css http getmobicss com a lightweight scalable mobile first css framework picnic css https picnicss com an invasive css library to get your style started pure https purecss io a set of small responsive css modules that you can use in every web project skeleton http getskeleton com a dead simple responsive boilerplate tachyons http tachyons io create fast loading highly readable and 100 responsive interfaces with as little css as possible wing https kbrsh github io wing a beautiful css framework designed for minimalists shim polyfill a name shim a x2191 nbsp x2191 nbsp x2191 toc core js https github com zloirock core js modular standard library for javascript includes polyfills for ecmascript 5 2015 2016 2017 ecmascript shims https github com es shims a community host for shims and polyfills that are compliant to ecmascript specs es5 shim https github com es shims es5 shim monkey patch a javascript context to contain all ecmascript 5 methods that can be faithfully emulated with a legacy javascript engine es6 shim https github com es shims es6 shim provides compatibility shims so that legacy javascript engines behave as closely as possible to ecmascript 6 es7 shim https github com es shims es7 shim contains shims that can be used to monkeypatch a javascript context to contain all ecmascript 7 methods that can be faithfully emulated with a legacy javascript engine intl js https github com andyearnshaw intl js compatibility implementation of the ecmascript internationalization api ecma 402 for javascript web development a name web dev a x2191 nbsp x2191 nbsp x2191 toc astro https astro build an all in one web framework for building fast content focused websites next js https nextjs org a javascript framework that lets you build server side rendering and static web applications using react zero https zeroserver io a web framework to simplify modern web development it s as simple as writing your code in a mix of node js react html mdx vue and static files and putting them all in a folder zero abstracts the usual project configuration for routing bundling and transpiling to make it easier to get started mobile development a name mobile dev a x2191 nbsp x2191 nbsp x2191 toc ionic https ionicframework com framework the open source mobile app development framework that makes it easy to build top quality native and progressive web apps with web technologies nativescript https www nativescript org an open source framework for building truly native mobile apps with javascript and css react native https facebook github io react native build native mobile apps using javascript and react desktop development a name desktop dev a x2191 nbsp x2191 nbsp x2191 toc electron https electronjs org a framework that lets you write cross platform desktop applications using javascript html and css nodegui https nodegui org an open source library for building cross platform native desktop applications with javascript and css like styling nodegui is based on qt5 and not chromium hence it is memory and cpu efficient react nodegui is a react renderer for nodegui nw js https nwjs io an app runtime based on chromium and node js you can write native apps in html and javascript with nw js proton native https proton native js org a react environment for cross platform native desktop apps data model state management library a name state management a x2191 nbsp x2191 nbsp x2191 toc breeze http www getbreezenow com breezejs the data management library for developers of rich client applications written in javascript if you store data in a database query and save those data as complex object graphs and share these graphs across multiple screens of your javascript client breeze is for you cerebral https cerebraljs com a declarative state and side effects management solution for popular javascript frameworks effector https effector now sh an effective multi store state manager for javascript apps that allows you to manage data in complex applications without the risk of inflating the monolithic central store with clear control flow good type support and high capacity api freactal https github com formidablelabs freactal a composable state management library for react jsdata https www js data io a framework agnostic datastore agnostic orm for node js and the browser microstates https github com microstates microstates js a functional runtime type system designed to ease state management in component based applications it allows you to declaratively compose application state from atomic state machines mobx https mobx js org a battle tested library that makes state management simple and scalable by transparently applying functional reactive programming nuclearjs https optimizely github io nuclear js reactive flux built with immutablejs data structures orbit https orbitjs com a composable data framework for managing the complex needs of today s web applications although orbit is primarily used as a flexible client side orm it can also be used server side in node js overmind https overmindjs org frictionless state management overmind aims for a developer experience where that is all you focus on reducing the orchestration of state management to a minimum redux https redux js org a predictable state container for javascript apps storeon https github com storeon storeon a tiny event based redux like state manager for react and preact transis https github com centro transis a javascript data modeling library useful for creating rich client side experiences undux https undux org a simple typesafe alternative to flux and redux use it to manage state and data for reactjs applications of all sizes unistore https github com developit unistore a tiny centralized state container with component bindings for preact react watermelondb https nozbe github io watermelondb build powerful react and react native apps that scale from hundreds to tens of thousands of records and remain fast redux based library a name redux library a x2191 nbsp x2191 nbsp x2191 toc easy peasy https easy peasy now sh provides you with an intuitive api to quickly and easily manage the state for your react application no configuration is required to support derived state api calls performance optimisation developer tools etc kea https keajs org a production grade state management framework built for react apps kea is built on top of redux and leverages its underlying functional principles redux toolkit https redux toolkit js org the official opinionated batteries included toolset for efficient redux development rematch https rematch github io rematch redux best practices without the boilerplate database a name database a x2191 nbsp x2191 nbsp x2191 toc alasql http alasql org javascript sql database for browser and node js handles both traditional relational tables and nested json data nosql export store and import data from localstorage indexeddb or excel datascript https github com tonsky datascript immutable database and datalog query engine for clojure clojurescript and js forerunnerdb http www forerunnerdb com a nosql javascript json database with a query language based on mongodb with some differences and runs on browsers and node js lokijs https github com techfort lokijs a document oriented database written in javascript its purpose is to store javascript objects as documents in a nosql fashion and retrieve them with a similar mechanism runs in node including cordova phonegap and node webkit nativescript and the browser lowdb https github com typicode lowdb a small local database for small projects powered by lodash api nanosql https nanosql io universal database layer for the client server mobile devices it s like lego for databases nedb https github com louischatriot nedb embedded persistent or in memory database for node js nw js electron and browsers 100 javascript no binary dependency pouchdb https pouchdb com an open source javascript database inspired by apache couchdb that is designed to run well within the browser it enables applications to store data locally while offline then synchronize it with couchdb and compatible servers when the application is back online keeping the user s data in sync no matter where they next login rxdb https rxdb info a realtime database for javascript applications rxdb is a nosql database for javascript applications like websites hybrid apps electron apps progressive web apps and nodejs tingodb http www tingodb com an embedded javascript in process filesystem or in memory database upwards compatible with mongodb at the api level internationalization i18n localization l10n a name i18n a x2191 nbsp x2191 nbsp x2191 toc fluent js https github com projectfluent fluent js a javascript implementation of project fluent https projectfluent org a localization framework designed to unleash the expressive power of the natural language formatjs https formatjs io a modular collection of javascript libraries for internationalization that are focused on formatting numbers dates and strings for displaying to people it includes a set of core libraries that build on the javascript intl built ins and industry wide i18n standards plus a set of integrations for common template and component libraries globalize https globalizejs com a javascript library for internationalization and localization that leverage the official unicode cldr json data globalize provides number formatting and parsing date and time formatting and parsing currency formatting message formatting icu message format pattern and plural support i18next https www i18next com an internationalization framework written in and for javascript it provides you with a complete solution to localize your product from web to mobile and desktop lingui https lingui js org an easy yet powerfull internationalization framework for global projects javascript utility library a name js utility library a x2191 nbsp x2191 nbsp x2191 toc 101 https github com tjmehta 101 a modern js utility library licia https licia liriliri io useful utility collection with zero dependencies lodash https lodash com a modern javascript utility library delivering modularity performance extras mout http moutjs com a collection of modular javascript utilities that can be used in the browser as amd modules or on node js sugar https sugarjs com a javascript utility library for working with native objects umbrella https github com thi ng umbrella a collection of functional programming libraries that can be composed together underscore http underscorejs org a javascript library that provides a whole mess of useful functional programming helpers without extending any built in objects javascript module system and loader a name loader a x2191 nbsp x2191 nbsp x2191 toc systemjs https github com systemjs systemjs dynamic es module loader amd curl js https github com cujojs curl outdated a small and very fast amd compliant asynchronous loader require js https requirejs org a javascript file and module loader commonjs cajon https github com requirejs cajon a javascript module loader for the browser that can load commonjs node and amd modules it is built on top of requirejs inject http www injectjs com outdated amd and cjs dependency management in the browser require1k https github com stuk require1k a minimal and yet practically useful commonjs node js require module loader for the browser in under 1000 bytes ecmascript 6 snowpack https www snowpack dev with snowpack you can build modern web apps using react vue etc without a bundler like webpack parcel rollup no more waiting for your bundler to rebuild your site instead every change is reflected in the browser instantly module and asset bundler a name bundler a x2191 nbsp x2191 nbsp x2191 toc browserify http browserify org lets you require modules in the browser by bundling up all of your dependencies esbuild https esbuild github io an extremely fast javascript bundler fusebox http fuse box org a bundler module loader that combines the power of webpack jspm and systemjs it will compile and bundle your code within a fraction of a second yet offering a comprehensive loader api gluejs http mixu net gluejs package node commonjs modules for the browser lasso js https github com lasso js lasso javascript module bundler that also provides first level support for optimally delivering javascript css images and other assets to the browser offers many different optimizations such as a bundling code splitting lazy loading conditional dependencies compression and fingerprinted resource urls microbundle https github com developit microbundle zero configuration bundler for tiny modules parcel https parceljs org blazing fast zero configuration web application bundler pika pack https github com pikapkg pack developer tool that uses simple pre configured build plugins to create your modern package poi https poi js org develop powerful web app with no build configs until you need rollup http rollupjs org a module bundler for javascript which compiles small pieces of code into something larger and more complex such as a library or application systemjs builder https github com systemjs builder provides a single file build for systemjs of mixed dependency module trees vite https vitejs dev a new breed of frontend build tool that significantly improves the frontend development experience webpack https webpack js org a module bundler its main purpose is to bundle javascript files for usage in a browser yet it is also capable of transforming bundling or packaging just about any resource or asset package manager a name package manager a x2191 nbsp x2191 nbsp x2191 toc bower https bower io outdated a package manager for the web duo http duojs org outdated github repository https github com duojs duo a next generation package manager that blends the best ideas from component browserify and go to make organizing and writing front end code quick and painless jspm https jspm io registry and format agnostic javascript package manager for the systemjs universal module loader npm https www npmjs com a package manager for javascript pnpm https pnpm js org fast disk space efficient package manager yarn https yarnpkg com fast reliable and secure dependency management css processor a name css processor a x2191 nbsp x2191 nbsp x2191 toc eqcss http elementqueries com a css extension for element queries more less http lesscss org the dynamic stylesheet language postcss http postcss org a tool for transforming css with javascript sass http sass lang com an extension of css adding nested rules variables mixins selector inheritance and more stylus http stylus lang com expressive robust feature rich language providing an efficient dynamic and expressive way to generate css css tool a name css tool a x2191 nbsp x2191 nbsp x2191 toc change svg color https change svg color edrini xyz github https github com prottoy2938 change svg color converts hex rgba hsla color to css filter and the css filter could be used to change the svg color css gradient https cssgradient io a website and free tool that lets you create a gradient background for websites keyframes https keyframes app a free bundle of tools to generate live preview different css properties plus some other web development tools smooth shadow https shadows brumm af make a smooth shadow linting validation checklist a name linting a x2191 nbsp x2191 nbsp x2191 toc front end checklist https frontendchecklist io an exhaustive list of all elements you need to have to test before launching your site html page to production knip https github com webpro knip finds unused files dependencies and exports in your javascript and typescript projects lint staged https github com okonet lint staged run linters against staged git files this project contains a script that will run arbitrary shell tasks with a list of staged files as an argument filtered by a specified glob pattern textlint https textlint github io the pluggable linting tool for text and markdown textlint is similar to eslint but it s for use with natural language webhint https webhint io a linting tool for the web web developer checklist http webdevchecklist com the ultimate checklist for all serious web developers building modern websites css csslint https github com csslint csslint a tool to help point out problems with your css code it does basic syntax checking as well as applying a set of rules to the code that look for problematic patterns or signs of inefficiency the rules are all pluggable so you can easily write your own or omit ones you don t want purgecss https purgecss com a tool to remove unused css from your project stylelint https stylelint io a mighty modern linter that helps you avoid errors and enforce conventions in your styles uncss https github com uncss uncss a tool that removes unused css from your stylesheets it works across multiple files and supports javascript injected css html html inspector https github com philipwalton html inspector a highly customizable code quality tool to help you write better markup htmlhint https github com htmlhint htmlhint the static code analysis tool you need for your html javascript and variants deadfile https github com m izadmehr deadfile simple util to find deadcode and unused files in any javascript project es5 es6 react vue depcheck https github com depcheck depcheck a tool for analyzing the dependencies in a project to see how each dependency is used which dependencies are useless and which dependencies are missing from package json eslint https eslint org the pluggable linting utility for javascript and jsx jshint https jshint com a tool that helps to detect errors and potential problems in your javascript code quick lint js https quick lint js com finds bugs in javascript programs lint any javascript file with no configuration tslint https palantir github io tslint an extensible static analysis tool that checks typescript code for readability maintainability and functionality errors it is widely supported across modern editors build systems and can be customized with your own lint rules configurations and formatters ts prune https github com nadeesha ts prune find potentially unused exports in your typescript project with zero configuration unimported https github com smeijer unimported find and fix dangling files and unused dependencies in your javascript projects xo https github com xojs xo opinionated but configurable eslint wrapper with lots of goodies included testing a name testing a x2191 nbsp x2191 nbsp x2191 toc ava https github com avajs ava a test runner for node js with a concise api detailed error output embrace of new language features and process isolation that let you write tests more effectively backstopjs https garris github io backstopjs automates visual regression testing of your responsive web ui by comparing dom screenshots over time chai https www chaijs com a bdd tdd assertion library for node and the browser that can be delightfully paired with any javascript testing framework codeceptjs https codecept io acceptance testing framework for nodejs codeceptjs is a testing framework for end to end testing with webdriver or others it abstracts browser interaction to simple steps which is written from a user perspective cypress https www cypress io a test engine that runs unit and integration tests in your browser enzyme https enzymejs github io enzyme a javascript testing utility for react that makes it easier to test your react components output you can also manipulate traverse and in some ways simulate runtime given the output gauge https gauge org a light weight cross platform test automation tool it provides the ability to author test cases in the business language hermione https github com gemini testing hermione a utility for integration testing of web pages using webdriverio and mocha intern https theintern io a complete test system for javascript designed to help you write and run consistent high quality test cases for your javascript libraries and applications istanbul https istanbul js org js code coverage tool that computes statement line function and branch coverage jasmine https jasmine github io a behavior driven development framework for testing javascript code jest https jestjs io a delightful javascript testing framework with a focus on simplicity karma http karma runner github io a tool that allows you to execute javascript code in multiple real browsers majestic https github com raathigesh majestic zero config gui for jest mocha https mochajs org simple flexible fun javascript test framework for node js the browser mock service worker https github com mswjs msw an api mocking library for browser and node js responsively app https responsively app a modified browser that helps in responsive web development qa wolf https www qawolf com a node js library for creating browser tests qunit https qunitjs com a powerful easy to use javascript unit testing framework sazerac https sazerac js org data driven testing for javascript it helps you create simple readable tests and works with jasmine jest and mocha taiko https taiko dev an open source node js library for testing modern web applications tape https github com substack tape tap producing test harness for node and browsers testcafe https devexpress github io testcafe a node js tool to automate end to end web testing testem https github com testem testem a test runner that makes javascript unit testing fun testing library https testing library com simple and complete testing utilities that encourage good testing practices and help you test ui components in a user centric way debug a name debug a x2191 nbsp x2191 nbsp x2191 toc eruda https eruda liriliri io console for mobile browsers fuite https github com nolanlawson fuite a cli tool for finding memory leaks in web apps ndb https github com googlechromelabs ndb an improved debugging experience for node js enabled by chrome devtools stacktrace js https www stacktracejs com generate parse and enhance javascript stack traces in all web browsers vorlon js http www vorlonjs com an open source extensible platform agnostic tool for remotely debugging and testing your javascript powered by node js and socket io weinre https people apache org pmuellr weinre docs latest a debugger for web pages like firebug for firefox and web inspector for webkit based browsers except it s designed to work remotely and in particular to allow you debug web pages on a mobile device such as a phone use new error stack or console trace to print stack trace see force stack traces with javascript https davidwalsh name javascript stack trace documentation a name documentation a x2191 nbsp x2191 nbsp x2191 toc docsify https docsify js org a magical documentation site generator documentation js http documentation js org the documentation system for modern javascript docusaurus https docusaurus io a project for easily building deploying and maintaining open source project websites docute https docute org the fastest way to create a documentation site for your project docz https www docz site it has never been so easy to document your things esdoc https esdoc org a documentation generator for javascript es6 jsdoc https jsdoc app an api documentation generator for javascript x0 https github com c8r x0 document develop react components without breaking a sweat yuidoc http yui github io yuidoc a node js application that generates api documentation from comments in source using a syntax similar to tools like javadoc and doxygen code processing a name code processing a x2191 nbsp x2191 nbsp x2191 toc prettier https prettier io an opinionated code formatter it enforces a consistent style by parsing your code and re printing it with its own rules that take the maximum line length into account wrapping code when necessary minification a name mini a x2191 nbsp x2191 nbsp x2191 toc minify http coderaiser github io minify a minifier of js css html and img files node minify https github com srod node minify a light node js module that compress javascript and css files css clean css https github com jakubpawlowicz clean css a fast and efficient css optimizer for node js platform and any modern browser crass https github com mattbasta crass a css minification pretty printing and general utility library written in js cssnano https github com ben eb cssnano a modern modular compression tool written on top of the postcss ecosystem csso https github com css csso a css minifier with structural optimizations csswring https github com hail2u node csswring a css minifier for postcss html htmlminifier https github com kangax html minifier a highly configurable well tested javascript based html minifier minimize https github com swaagie minimize a html minifier based on the node htmlparser minimize is focussed on html5 and will not support older html drafts images compressimage io https compressimage io compress jpg and png images at light speed with browser based image compressor private works offline compressor io https compressor io fast efficient online image compression imageoptim https imageoptim com mac saves disk space bandwidth by compressing images without losing quality squoosh https squoosh app an image compression web app that allows you to dive into the advanced options provided by various image compressors svgo https github com svg svgo a nodejs based tool for optimizing svg vector graphics files javascript babel minify https github com babel minify an es6 aware minifier based on the babel toolchain uglifyjs https github com mishoo uglifyjs2 a javascript parser minifier compressor and beautifier toolkit unminifier a name unmini a x2191 nbsp x2191 nbsp x2191 toc unminify https unminify com free tool to unminify unpack deobfuscate javascript css html xml and json code making it readable and pretty task runner build tool a name task runner a x2191 nbsp x2191 nbsp x2191 toc brunch https github com brunch brunch fast front end web app build tool with simple declarative config seamless incremental compilation for rapid development an opinionated pipeline and workflow and core support for source maps cross env https github com kentcdodds cross env run scripts that set and use environment variables across platforms grunion https github com hypercubed grunion run multiple commands using glob patterns grunt https gruntjs com the javascript task runner gulp https gulpjs com a toolkit for automating painful or time consuming tasks in your development workflow jake https jakejs com a simple and flexible javascript build tool for nodejs just https microsoft github io just a library that organizes build tasks for your js projects it consists of a build task build definition library sane preset build flows for node and browser projects featuring typescript webpack and jest project scaffold tool that generates no ejection needed repos that tracks template changes ncc https github com zeit ncc simple cli for compiling a node js module into a single file together with all its dependencies gcc style nexe https github com nexe nexe a command line utility that compiles your node js application into a single executable file npm run all https github com mysticatea npm run all a cli tool to run multiple npm scripts in parallel or sequential nps https github com kentcdodds nps all the benefits of npm scripts without the cost of a bloated package json and limits of json npx https github com npm npx execute npm package binaries pkg https github com zeit pkg this command line interface enables you to package your node js project into an executable that can be run even on devices without node js installed scripty https github com testdouble scripty a tool to help extract npm scripts into their own files shx https github com shelljs shx a wrapper around shelljs unix commands providing an easy solution for simple unix like cross platform commands in npm package scripts taskr https github com lukeed taskr a fast concurrency focused task runner xclap https github com jchip xclap an advanced and flexible javascript task executor and build tool ygor https github com shannonmoeller ygor javascript task runner for when npm run isn t enough and everything else is too much automation a name automation a x2191 nbsp x2191 nbsp x2191 toc np https github com sindresorhus np a better npm publish semantic release https github com semantic release semantic release automates the whole package release workflow including determining the next version number generating the release notes and publishing the package standard version https github com conventional changelog standard version automate versioning and changelog generation with semver https semver org and conventional commit messages https conventionalcommits org boilerplate scaffolding a name boilerplate a x2191 nbsp x2191 nbsp x2191 toc create react app https create react app dev create react apps with no build configuration create react library https github com transitive bullshit create react library cli for easily creating reusable react libraries degit https github com rich harris degit straightforward project scaffolding degit makes copies of git repositories fullstack typescript https github com gilamran fullstack typescript fullstack react with typescript starter kit neutrino https neutrinojs org a companion tool which lets you build web and node js applications with shared presets or configurations it intends to make the process of initializing and building projects much simpler by providing minimal development dependencies nwb https github com insin nwb a toolkit for react preact inferno vanilla js apps react libraries and other npm modules for the web with no configuration until you need it react starter kit https reactstarter com an opinionated boilerplate for web development built on top of node js express graphql and react containing modern web development tools such as webpack babel and browsersync tsdx https github com jaredpalmer tsdx a zero config cli that helps you develop test and publish modern typescript packages with ease component development a name component dev a x2191 nbsp x2191 nbsp x2191 toc bluekit https react bluekit herokuapp com automatically generates a library from your react components with editable props and live preview component playground https github com formidablelabs component playground a component for rendering react components and es6 code with editable source and live preview kit https github com c8r kit tools for developing documenting and testing react component libraries ladle https www ladle dev develop and test your react stories faster ladle is a drop in alternative to storybook it is a tool for developing and testing your react components in an environement that s isolated and faster than most real world applications preview js https previewjs com preview ui components and storybook stories in your ide instantly react cosmos https github com react cosmos react cosmos dev tool for creating reusable react components react live https github com formidablelabs react live brings you the ability to render react components and present the user with editable source code and live preview react styleguidist https react styleguidist js org isolated react component development environment with a living style guide storybook https storybook js org a development environment for ui components it allows you to browse a component library view the different states of each component and interactively develop and test components design a name design a x2191 nbsp x2191 nbsp x2191 toc playroom https github com seek oss playroom simultaneously design across a variety of themes and screen sizes powered by jsx and your own component library playroom allows you to create a zero install code oriented design environment built into a standalone bundle that can be deployed alongside your existing design system documentation graphics image editor a name image editor a x2191 nbsp x2191 nbsp x2191 toc gimp https www gimp org a cross platform image editor available for gnu linux os x windows and more operating systems inkscape https inkscape org a free and open source vector graphics editor for gnu linux windows and macos x it offers a rich set of features and is widely used for both artistic and technical illustrations such as cartoons clip art logos typography diagramming and flowcharting krita https krita org a professional free and open source painting program it is made by artists that want to see affordable art tools for everyone paint net https www getpaint net image and photo editing software for pcs that run windows images icons a name images a x2191 nbsp x2191 nbsp x2191 toc css gg https css gg open source css svg and figma ui icons available in svg sprite styled components npm api eva icons https akveo github io eva icons a pack of more than 480 beautifully crafted open source icons for common actions and items icons are provided in two visual types fill and outline and in several formats including png svg font sketch etc heroicons https heroicons dev a set of free mit licensed high quality svg icons for ui development iconmonstr https iconmonstr com free monstrously big and continuously growing source of simple icons icono https saeedalipoor github io icono pure css icons with only one element iconoir https iconoir com a high quality selection of free icons icons8 https icons8 com free icons photos vectors music and tools iconsear ch https iconsear ch search html search engine for svg icons ikonate https www ikonate com fully customisable accessible well optimised vector icons line icons https lineicons com handcrafted line icons for modern user interfaces logosear ch https logosear ch search html search engine for svg logos lorem picsum https picsum photos the lorem ipsum for photos easy to use stylish image placeholders just add your desired image size width height after our url and you ll get a random image remix icon https remixicon com a set of open source neutral style system symbols for designers and developers super tiny icons https github com edent supertinyicons miniscule svg versions of your favourite website and app logos svg porn https svgporn com a huge collection of svg logos tabler icons https tabler icons io free and open source icons designed to make your website or app attractive visually consistent and simply beautiful vectorlogozone https www vectorlogo zone consistently formatted svg logos analysis performance optimization a name analysis a x2191 nbsp x2191 nbsp x2191 toc bundle buddy https github com samccone bundle buddy a tool to help you find source code duplication across your javascript chunks splits bundle phobia https bundlephobia com know the performance impact of including an npm package in your app s bundle front end performance checklist https github com thedaviddias front end performance checklist an exhaustive list of elements you should check or at least be aware of as a front end developer and apply to your project lighthouse https developers google com web tools lighthouse an open source automated tool for improving the quality of web pages it has audits for performance accessibility progressive web apps and more optimize your libraries with webpack https github com googlechromelabs webpack libs optimizations tips to make your webpack bundle smaller package phobia https packagephobia com reports the size of an npm package before you install it this is useful for inspecting potential dependencies or devdependencies without using up precious disk space or waiting minutes for npm install size limit https github com ai size limit calculate the real cost of your js for end users and throws an error if the cost exceeds the limit source map explorer https github com danvk source map explorer analyze and debug space usage through source maps the source map explorer determines which file each byte in your minified code came from waterfaller https waterfaller dev focuses on issues in the network waterfall and provides recommendations for improvement webpack bundle analyzer https github com webpack contrib webpack bundle analyzer webpack plugin and cli utility that represents bundle content as convenient interactive zoomable treemap webpack visualizer https github com chrisbateman webpack visualizer visualize and analyze your webpack bundle to see which modules are taking up space and which might be duplicates webpagetest https www webpagetest org run a free website speed test from multiple locations around the globe using real browsers and at real consumer connection speeds yellow lab tools https yellowlab tools allows you to test a webpage via an url and detects performance and front end code quality issues technologies support a name tech support a x2191 nbsp x2191 nbsp x2191 toc can i devtools https www canidev tools it is like caniuse but for the browser devtools can i email https www caniemail com provides email clients support tables for html and css features can i use https caniuse com provides up to date browser support tables for support of front end web technologies on desktop and mobile web browsers network a name net a x2191 nbsp x2191 nbsp x2191 toc httpie https httpie org a command line http client with an intuitive ui json support syntax highlighting wget like downloads plugins and more insomnia https insomnia rest cross platform http and graphql client lightproxy https lightproxy org cross platform web debugging proxy lightproxy is a local proxy packet capture software postwoman https postwoman io a free fast and beautiful api request builder web alternative to postman wireshark https www wireshark org the world s foremost and widely used network protocol analyzer version control a name version control a x2191 nbsp x2191 nbsp x2191 toc git a name git a x2191 nbsp x2191 nbsp x2191 toc git extras https github com tj git extras git utilities repo summary repl changelog population author commit percentages and more husky https github com typicode husky git hooks made easy husky can prevent bad git commit git push and more sourcetree https www sourcetreeapp com visualize and manage your repositories through simple git gui tortoisegit https tortoisegit org a windows shell interface to git provides overlay icons showing the file status a powerful context menu for git and much more development server a name dev server a x2191 nbsp x2191 nbsp x2191 toc node js based a name dev server node a x2191 nbsp x2191 nbsp x2191 toc browsersync https www browsersync io keep multiple browsers devices in sync when building websites easymock server https github com cyberagent node easymock a simple but powerful mock server fenix http fenixwebserver com a simple and visual static web server with collaboration features freddie https github com scytl freddie front end development server http server https github com http party http server a simple zero configuration command line http server json server https github com typicode json server get a full fake rest api with zero coding live server http tapiov net live server a simple development http server with live reload capability lite server https github com johnpapa lite server lightweight development only node server that serves a web app lite server is a simple customized wrapper around browsersync to make it easy to serve spas local web server https github com lwsjs local web server the modular web server for productive full stack development mockit https mockit netlify com a tool to quickly create mocked apis puer https github com leeluolee puer more than a live reload server built for efficient frontend development servedir https github com evanw servedir a simple node web server for offline development and testing running servedir from a directory will create a quick local web server server with benefits https github com galbi101 server with benefits a static node js file web server with options for proxing requests and delaying mocking responses superstatic with proxy https github com colinbate superstatic with proxy an enhanced static web server that was built to power this version adds in the superstatic proxy by default with php support a name dev server php a x2191 nbsp x2191 nbsp x2191 toc appserv http www appservnetwork com a full featured of apache mysql php phpmyadmin devserver http www easyphp org a complete and ready to use development environment devserver is portable modular fully configurable and easy to update and extend laragon https laragon org a portable isolated fast powerful universal development environment for php node js python java go ruby it is fast lightweight easy to use and easy to extend uniform server http www uniformserver com a lightweight server solution for running a web server under the windowsos uwamp http www uwamp com en free wamp server with apache mysql php and sqlite vertrigoserv https www vswamp com a complete free wamp server allowing php development for windows wampserver http www wampserver com en a windows web development environment it allows you to create web applications with apache2 php and a mysql database wp xm http wpn xm org a free and open source web server solution stack for professional php development on windows wtserver http wtserver wtriple com a portable preconfigured lightweight fast and stable server stack for developing php mysql applications on windows based on the excellent webserver nginx xampp https www apachefriends org a completely free easy to install apache distribution containing mariadb php and perl node js version management a name node manage a x2191 nbsp x2191 nbsp x2191 toc n https github com tj n interactively manage your node js versions node package https www npmjs com package node npm package that installs a node binary into your project which means you can have a local version of node that is different than your system s and manage node as a normal dependency nodenv https github com nodenv nodenv manage multiple nodejs versions nodist https github com marcelklehr nodist a node js and npm version manager for the windows nvm node version manager https github com creationix nvm simple bash script to manage multiple active node js versions nvm windows https github com coreybutler nvm windows a node js version management utility for windows nvs node version switcher https github com jasongin nvs a cross platform utility for switching between different versions and forks of node js nvs is itself written in node javascript editor ide a name editor a x2191 nbsp x2191 nbsp x2191 toc atom https atom io a text editor that s modern approachable yet hackable to the core a tool you can customize to do anything but also use productively without ever touching a config file brackets http brackets io with focused visual tools and preprocessor support brackets is a modern text editor that makes it easy to design in the browser it s crafted from the ground up for web designers and front end developers geany https www geany org a small and lightweight integrated development environment leo http leoeditor com a pim ide and outliner that accelerates the work flow of programmers authors and web designers light table http lighttable com a next generation code editor that connects you to your creation with instant feedback light table is very customizable and can display anything a chromium browser can notepad https notepad plus plus org a free source code editor and notepad replacement that supports several languages pspad https www pspad com text editor for developers for microsoft windows systems rj texted https www rj texted se a full featured text and source editor with unicode support it is also a very powerful web php asp javascript html and css development editor visual studio code https code visualstudio com a new type of tool that combines the simplicity of a code editor with what developers need for their core edit build debug cycle code provides comprehensive editing and debugging support an extensibility model and lightweight integration with existing tools playground interactive computing a name playground a x2191 nbsp x2191 nbsp x2191 toc nteract https nteract io sdks applications and libraries that help you and your team make the most of interactive notebooks and repls quokka https quokkajs com a developer productivity tool for rapid javascript typescript prototyping runtime values are updated and displayed in your ide next to your code as you type runjs https runjs app a javascript playground that auto evaluates your code as you type and outputs the results to a console pane online development playground a name online dev a x2191 nbsp x2191 nbsp x2191 toc codebunk https codebunk com the ultimate online coding interview tool collaborative editor compiler chat codecollab https codecollab io an online real time collaborative code editor and compiler our web based application allows users to collaborate in real time over the internet codepen https codepen io a playground for the front end side of the web it s a place to build and deploy a website show off your work build test cases and find inspiration codesandbox https codesandbox io an online web application editor makes it easier to create share and reuse web projects with others codeshare https codeshare io an online code editor for interviews troubleshooting teaching more esnextbin https esnextb in create browser programs in es2015 code and import modules from npm in browser flems io https flems io a playground for web development it s ideal for prototyping ideas sharing working front end code examples also see flems module https github com porsager flems which can be used for easy self hosting or embedding glitch https glitch com the friendly community where everyone can discover and create the best stuff on the web js bin https jsbin com an open source collaborative web development debugging tool write code and have it both save in real time but also render a full preview in real time jsfiddle https jsfiddle net an online playground for your javascript html css repl it https repl it simple reliable and portable cloud coding interface a community of teachers students and engineers runkit https runkit com a node playground in your browser stackblitz https stackblitz com the online code editor for web apps online tool a name online tool a x2191 nbsp x2191 nbsp x2191 toc extendsclass https extendsclass com free online toolbox for developers you have at your disposal syntax validators code formatters testers http clients mock server but also a sqlite browser online gradient generator https angrytools com gradient create gradient code in css rgba hex canvas svg swiftui and android xml format in addition you can also generate gradient image and download windframe https www devwares com windframe online visual builder for rapidly building and prototyping components and websites using tailwind css site generator a name site generator a x2191 nbsp x2191 nbsp x2191 toc cms js http chrisdiana github io cms js fully client side javascript site generator in the spirit of jekyll that uses plain ol html css and javascript to generate your website docpad https github com docpad docpad a dynamic static site generator that is a content management system that takes content from several sources like files on your computer and renders them into incredibly fast static output elder js https github com elderjs elderjs an opinionated static site generator and web framework for svelte built with seo in mind gatsby https www gatsbyjs com blazing fast static site generator for react gridsome https gridsome org a vue powered static site generator for building cdn ready websites for any headless cms local files or apis hexo https hexo io a fast simple and powerful blog framework you write posts in markdown or other languages and hexo generates static files with a beautiful theme in seconds hugo https gohugo io a static html and css website generator written in go it is optimized for speed ease of use and configurability hugo takes a directory with content and templates and renders them into a full html website lektor https www getlektor com a flexible and powerful static content management system for building complex and beautiful websites out of flat files emulator simulator a name emulator a x2191 nbsp x2191 nbsp x2191 toc responsinator https www responsinator com helps website makers quickly get an indication of how their responsive site will look on the most popular devices api a name api a x2191 nbsp x2191 nbsp x2191 toc apis guru https apis guru browse apis wikipedia for web apis programmableweb api directory https www programmableweb com apis directory directory where developers can search for apis to include in their next software development project public apis https github com public apis public apis a collective list of free apis for use in software and web development public apis io https public apis io a directory of free public open rest apis rapidapi https rapidapi com find and connect to thousands of apis track and manage all of your api connections in one place rapidapi lets you manage all your api integrations from one place and gives you real time performance metrics swagger https swagger io a powerful yet easy to use suite of api developer tools for teams and individuals enabling development across the entire api lifecycle from design and documentation to test and deployment browser extension a name browser extension a x2191 nbsp x2191 nbsp x2191 toc chrome 25 essential chrome extensions for web designers https envato com blog chrome extensions web design checkbot https www checkbot io crawls your site testing pages follow 50 seo speed and security best practices css peeper https csspeeper com smart css viewer tailored for designers js bundle size https github com vicrazumov js bundle size automatically adds javascript bundle size data to npm and github project pages z context https github com gwwar z context displays stacking contexts and z index values in the elements panel benchmark a name benchmark a x2191 nbsp x2191 nbsp x2191 toc css minification benchmark http goalsmashers github io css minification benchmark js web frameworks benchmark https github com krausest js framework benchmark a comparison of the perfomance of popular javascript frameworks ui benchmark https localvoid github io uibench hosting cloud services a name hosting a x2191 nbsp x2191 nbsp x2191 toc 000webhost https www 000webhost com hostinger ru https www hostinger ru zero cost website hosting with php mysql cpanel no ads 5apps deploy https 5apps com deploy a turn key deployment and hosting platform for client side web apps backendless https backendless com a leading mbaas and powerful mobile application development platform that enables rapid development of feature rich mobile desktop and browser based applications cloudant https www ibm com cloud cloudant a highly scalable and performant json database cloudnode https cloudno de a place to get your javascript web applications up and running extendsclass https extendsclass com json storage html a simple json storage firebase https firebase google com a cloud hosted database data is synchronized in realtime to every connected client hackmd https hackmd io best way to share knowledge in markdown heroku https www heroku com a cloud platform that lets companies build deliver monitor and scale apps jsonbin https jsonbin io a free json storage and json hosting service jsonserve https jsonserve com host your json easily and use in your apps microsoft azure https azure microsoft com en us services app service quickly create powerful cloud apps for web and mobile clients netlify https www netlify com builds deploys and hosts your front end now https zeit co now allows you to take your javascript node js or docker powered websites applications and services to the cloud with ease speed and reliability nuclino https www nuclino com the easiest way to organize and share knowledge in teams create real time collaborative documents and connect them instantly like a wiki use the tree board and graph view to explore and organize your knowledge visually it s great for meeting notes product requirements docs decisions and more openshift https www openshift com red hat s platform as a service paas that allows developers to quickly develop host and scale applications in a cloud environment pastebin https pastebin com a website where you can store any text online for easy sharing rentry co https rentry co a pastebin publishing service with markdown support preview custom urls and editing fast simple and free surge http surge sh static web publishing for front end developers code cdn a name code cdn a x2191 nbsp x2191 nbsp x2191 toc esm https esm sh a fast global content delivery network for npm packages with es module format jsdelivr https www jsdelivr com a free fast and reliable open source cdn for npm github skypack https www skypack dev load optimized npm packages with no install and no build tools unpkg https unpkg com a fast global content delivery network for everything on npm use it to quickly and easily load any file from any package guide reference practices recipes a name guide a x2191 nbsp x2191 nbsp x2191 toc 100 coding interview questions for programmers https codeburst io 100 coding interview questions for programmers b1cf74885fb7 solve these frequently asked coding problems to do well on your next programming job interviews 30 seconds of code https www 30secondsofcode org short code snippets for all your development needs 30 seconds of interviews https 30secondsofinterviews org a curated collection of common interview questions to help you prepare for your next interview checkbot web best practices https www checkbot io guide details 50 seo speed and security web best practices devdocs https devdocs io combines multiple api documentations in a fast organized and searchable interface every programmer should know https github com mtdvio every programmer should know a collection of mostly technical things every software developer should know front end interview handbook https github com yangshun front end interview handbook almost complete answers to front end job interview questions which you can use to interview potential candidates test yourself or completely ignore front end developer interview questions https h5bp org front end developer interview questions a list of helpful front end related questions you can use to interview potential candidates or test yourself grab front end guide https github com grab front end guide study guide and introduction to the modern front end stack overapi com https overapi com collecting all cheat sheets project guidelines https github com elsewhencode project guidelines a list of guidelines that works really well with most javascript projects service worker cookbook https serviceworke rs a collection of working practical examples of using service workers in modern web sites spellbook of modern web dev https github com dexteryy spellbook of modern webdev a big picture thesaurus and taxonomy of modern javascript web development tech interview handbook https www techinterviewhandbook org carefully curated content to help you ace your next technical interview with a focus on algorithms unix toolbox http devdoc net linux unixtoolbox html a collection of unix linux bsd commands and tasks which are useful for it work or for advanced users this is a practical guide with concise explanations however the reader is supposed to know what s he is doing webglossary info https webglossary info large web development glossary css a name css guide a x2191 nbsp x2191 nbsp x2191 toc 30 seconds of css https www 30secondsofcode org css a curated collection of useful css snippets you can understand in 30 seconds or less a complete guide to css functions https css tricks com complete guide to css functions bootstrap cheatsheet https bootstrap cheatsheet themeselection com an interactive list of bootstrap classes variables and mixins css protips https github com allthingssmitty css protips a collection of tips to help take your css skills pro css tricks https css tricks com a site about all things web design and development css triggers https csstriggers com a reference for the render impact of mutating css properties cssdb https cssdb org a comprehensive list of css features and their positions in the process of becoming implemented web standards modern css https moderncss dev modern css solutions for old css problems solved by flexbox https philipwalton github io solved by flexbox a showcase of problems once hard or impossible to solve with css alone now made trivially easy with flexbox the complete guide to css media queries https polypane app blog the complete guide to css media queries html a name html guide a x2191 nbsp x2191 nbsp x2191 toc html tips https markodenic com html tips some very useful html tips javascript a name js guide a x2191 nbsp x2191 nbsp x2191 toc 1loc https 1loc dev favorite javascript utilities in single line of code 30 seconds of javascript https www 30secondsofcode org js curated collection of useful javascript snippets that you can understand in 30 seconds or less 33 concepts every javascript developer should know https github com leonardomso 33 js concepts this repository was created with the intention of helping developers master their concepts in javascript it is not a requirement but a guide for future studies javascript algorithms and data structures https github com trekhleb javascript algorithms javascript based examples of many popular algorithms and data structures javascript clean code https github com ryanmcdermott clean code javascript software engineering principles from robert c martin s book clean code adapted for javascript javascript garden https shamansir github io javascript garden a growing collection of documentation about the most quirky parts of the javascript programming language javascript interview questions answers https github com sudheerj javascript interview questions list of 1000 javascript interview questions javascript questions https github com lydiahallie javascript questions a long list of advanced javascript questions and their explanations from basic to advanced test how well you know javascript refresh your knowledge a bit or prepare for your coding interview js tips https www jstips co a collection of useful daily javascript tips that will allow you to improve your code writing modern js cheatsheet https mbeaudru github io modern js cheatsheet cheatsheet for the javascript knowledge you will frequently encounter in modern projects node js best practices https github com goldbergyoni nodebestpractices a summary and curation of the top ranked content on node js best practices the modern javascript tutorial https javascript info wtfjs https github com denysdovhan wtfjs a list of funny and tricky javascript examples typescript a name ts guide a x2191 nbsp x2191 nbsp x2191 toc typescript cheatsheet https rmolinamir github io typescript cheatsheet a set of typescript related notes used for quick reference the cheatsheet contains references to types classes decorators and many other typescript related subjects typescript cheatsheets https github com typescript cheatsheets community curated cheatsheets for experienced js developers to share knowledge and copy paste recipes for common usecases typescript deep dive https basarat gitbook io typescript the definitive guide to typescript books a name books a x2191 nbsp x2191 nbsp x2191 toc data structures and algorithms in javascript https github com amejiarosario dsa js data structures and algorithms in javascript data structures and algorithms explained and implemented in javascript essential image optimization https images guide freely available programming books https github com ebookfoundation free programming books list of free learning resources front end developer handbook https frontendmasters com books front end handbook 2019 a guide that anyone could use to learn about the practice of front end development high performance browser networking https hpbn co provides a hands on overview of what every web developer needs to know about the various types of networks wifi 3g 4g transport protocols udp tcp and tls application protocols http 1 1 http 2 and apis available in the browser xhr websocket webrtc and more to deliver the best fast reliable and resilient user experience how to be a programmer https www gitbook com book braydie how to be a programmer javascript allong https leanpub com javascriptallongesix read a book about programming with functions mostly adequate guide to functional programming https github com mostlyadequate mostly adequate guide a book on the functional paradigm in general with javascript examples patterns dev https www patterns dev free book on design patterns and component patterns for building powerful web apps with vanilla javascript and react react in patterns https legacy gitbook com book krasimir react in patterns details a book about common design patterns used while developing with react it includes techniques for composition data flow dependency management and more survivejs https survivejs com books about react webpack and maintenance of javascript code the complete javascript handbook https www freecodecamp org news the complete javascript handbook f26b2c71719c learn 80 of javascript in 20 of the time the javascript way https github com thejsway thejsway a gentle introduction to an essential language examples a name examples a x2191 nbsp x2191 nbsp x2191 toc hacker news readers as progressive web apps https hnpwa com a list of unofficial hacker news clients built with a number of popular javascript frameworks and libraries each implementation is a complete progressive web app that utilizes different progressive technologies to provide a fast reliable and engaging experience realworld https github com gothinkster realworld see how the exact same medium com clone is built using any of our supported frontends and backends simpl info https simpl info simplest possible examples of html css and javascript todomvc https todomvc com helping you select an mv framework vanilla web projects https github com bradtraversy vanillawebprojects mini projects built with html5 css javascript no frameworks or libraries css a name css examples a x2191 nbsp x2191 nbsp x2191 toc css arrows from codepen https freebiesupply com blog css arrows a list of css arrows from codepen css background patterns https www magicpattern design tools css backgrounds beautiful pure css background patterns cssfx https cssfx netlify app beautifully simple click to copy css effects a carefully crafted collection designed with a focus on fluidity simplicity and ease of use powered by css with minimal markup css layout https csslayout io popular layouts patterns made with css drop in minimal css https dohliam github io dropin minimal css an overview of barebones drop in minimal css boilerplate frameworks spinkit https tobiasahlin com spinkit a collection of loading indicators animated with css the shapes of css https css tricks com the shapes of css lots of shapes in css with only a single html element transition css https www transition style easy transitions with clip path universe of ui elements https uiverse io css buttons checkboxes and more choose from numerous ui components and get the css for the ones you like ui snippets https ui snippets dev a collection of ui snippets webgradients https webgradients com a free collection of 180 linear gradients that you can use as content backdrops in any part of your website whirl https whirl netlify app css loading animations with minimal effort html a name html examples a x2191 nbsp x2191 nbsp x2191 toc html dom https htmldom dev common tasks of managing html dom with vanilla javascript sneat free bootstrap html admin template https github com themeselection sneat html admin template free open source rasy to use bootstrap 5 html admin template with elegant design unique layout news digest a name news a x2191 nbsp x2191 nbsp x2191 toc frontend dogma https frontenddogma com daily news and weekly tools https frontenddogma com tools for frontend development frontend weekly https frontendweekly co the best articles links and news related to frontend development javascript weekly https javascriptweekly com a newsletter of javascript articles news and cool projects useful articles resources a name resources a x2191 nbsp x2191 nbsp x2191 toc 120 places to find creative commons media https www sitepoint com creative commons sources resources to search for audio video images and more for use in a project awesome algorithms https github com tayllan awesome algorithms a curated list of awesome places to learn and or practice algorithms inside look at modern web browser https developer chrome com blog inside browser part1 keep a changelog https keepachangelog com make it easier for users and contributors to see precisely what notable changes have been made between each release or version of the project overview of the renderingng architecture https developer chrome com blog renderingng architecture overview of the chrome renderingng architecture goals and key properties the cost of small modules https nolanlawson com 2016 08 15 the cost of small modules outdated demonstrates that small modules can have a surprisingly high performance cost depending on your choice of bundler and module system the cost of transpiling es2015 in 2016 https github com samccone the cost of transpiling es2015 in 2016 outdated what do the popular javascript tools depend on https www telerik com blogs popular javascript tools depend outdated why performance matters https developers google com web fundamentals performance why performance matters table of contents x2191 toc | frontend front-end development tools list javascript css html js framework library tool toolkit catalog | front_end |
nsis | nsis build test and publish https github com kichik nsis actions workflows build yml badge svg https github com kichik nsis actions workflows build yml copy from sourceforge subversion https github com kichik nsis actions workflows copy svn yml badge svg https github com kichik nsis actions workflows copy svn yml nsis nullsoft scriptable install system is a professional open source system to create windows installers it is designed to be as small and flexible as possible and is therefore very suitable for internet distribution external links simple tutorial https nsis sourceforge io simple tutorials nsis homepage https nsis sourceforge io user manual https nsis sourceforge io docs | windows installer scripting-language build-tool | os |
MachineLearningWithPython | machinelearningwithpython starter files for pluralsight course understanding machine learning with python edit history jan 05 2019 updated references to deprecated functions in pima prediction with reload ipynb | ai |
|
prompt-engineering | brex s https brex com prompt engineering guide this guide was created by brex for internal purposes it s based on lessons learned from researching and creating large language model llm prompts for production use cases it covers the history around llms as well as strategies guidelines and safety recommendations for working with and building programmatic systems on top of large language models like openai s gpt 4 https openai com research gpt 4 the examples in this document were generated with a non deterministic language model and the same examples may give you different results this is a living document the state of the art best practices and strategies around llms are evolving rapidly every day discussion and suggestions for improvements are encouraged table of contents what is a large language model what is a large language model llm a brief incomplete and somewhat incorrect history of language models a brief incomplete and somewhat incorrect history of language models pre 2000 s pre 2000s mid 2000 s mid 2000s early 2010 s early 2010s late 2010 s late 2010s 2020 s 2020s what is a prompt what is a prompt hidden prompts hidden prompts tokens tokens token limits token limits prompt hacking prompt hacking jailbreaks jailbreaks leaks leaks why do we need prompt engineering why do we need prompt engineering give a bot a fish give a bot a fish semantic search semantic search teach a bot to fish teach a bot to fish command grammars command grammars react react gpt 4 vs gpt 3 5 gpt 4 vs gpt 35 strategies strategies embedding data embedding data simple lists simple lists markdown tables markdown tables json json freeform text freeform text nested data nested data citations citations programmatic consumption programmatic consumption chain of thought chain of thought averaging averaging interpreting code interpreting code delimiters delimiters fine tuning fine tuning downsides downsides additional resources additional resources what is a large language model llm a large language model is a prediction engine that takes a sequence of words and tries to predict the most likely sequence to come after that sequence 1 it does this by assigning a probability to likely next sequences and then samples from those to choose one 2 the process repeats until some stopping criteria is met large language models learn these probabilities by training on large corpuses of text a consequence of this is that the models will cater to some use cases better than others e g if it s trained on github data it ll understand the probabilities of sequences in source code really well another consequence is that the model may generate statements that seem plausible but are actually just random without being grounded in reality as language models become more accurate at predicting sequences many surprising abilities emerge https www assemblyai com blog emergent abilities of large language models 1 language models actually use tokens not words a token roughly maps to a syllable in a word or about 4 characters 2 there are many different pruning and sampling strategies to alter the behavior and performance of the sequences a brief incomplete and somewhat incorrect history of language models pushpin skip to here what is a prompt if you d like to jump past the history of language models this section is for the curious minded though may also help you understand the reasoning behind the advice that follows pre 2000 s language models https en wikipedia org wiki language model model types have existed for decades though traditional language models e g n gram models https en wikipedia org wiki n gram language model have many deficiencies in terms of an explosion of state space the curse of dimensionality https en wikipedia org wiki curse of dimensionality and working with novel phrases that they ve never seen sparsity plainly older language models can generate text that vaguely resembles the statistics of human generated text but there is no consistency within the output and a reader will quickly realize it s all gibberish n gram models also don t scale to large values of n so are inherently limited mid 2000 s in 2007 geoffrey hinton famous for popularizing backpropagation in 1980 s published an important advancement in training neural networks http www cs toronto edu fritz absps tics pdf that unlocked much deeper networks applying these simple deep neural networks to language modeling helped alleviate some of problems with language models they represented nuanced arbitrary concepts in a finite space and continuous way gracefully handling sequences not seen in the training corpus these simple neural networks learned the probabilities of their training corpus well but the output would statistically match the training data and generally not be coherent relative to the input sequence early 2010 s although they were first introduced in 1995 long short term memory lstm networks https en wikipedia org wiki long short term memory found their time to shine in the 2010 s lstms allowed models to process arbitrary length sequences and importantly alter their internal state dynamically as they processed the input to remember previous things they saw this minor tweak led to remarkable improvements in 2015 andrej karpathy famously wrote about creating a character level lstm http karpathy github io 2015 05 21 rnn effectiveness that performed far better than it had any right to lstms have seemingly magical abilities but struggle with long term dependencies if you asked it to complete the sentence in france we traveled around ate many pastries drank lots of wine lots more text but never learned how to speak the model might struggle with predicting french they also process input one token at a time so are inherently sequential slow to train and the nth token only knows about the n 1 tokens prior to it late 2010 s in 2017 google wrote a paper attention is all you need https arxiv org pdf 1706 03762 pdf that introduced transformer networks https en wikipedia org wiki transformer machine learning model and kicked off a massive revolution in natural language processing overnight machines could suddenly do tasks like translating between languages nearly as good as sometimes better than humans transformers are highly parallelizable and introduce a mechanism called attention for the model to efficiently place emphasis on specific parts of the input transformers analyze the entire input all at once in parallel choosing which parts are most important and influential every output token is influenced by every input token transformers are highly parallelizable efficient to train and produce astounding results a downside to transformers is that they have a fixed input and output size the context window and computation increases quadratically with the size of this window in some cases memory does as well 3 transformers are not the end of the road but the vast majority of recent improvements in natural language processing have involved them there is still abundant active research on various ways of implementing and applying them such as amazon s alexatm 20b https www amazon science blog 20b parameter alexa model sets new marks in few shot learning which outperforms gpt 3 in a number of tasks and is an order of magnitude smaller in its number of parameters 3 there are more recent variations to make these more compute and memory efficient but remains an active area of research 2020 s while technically starting in 2018 the theme of the 2020 s has been generative pre trained models more famously known as gpt one year after the attention is all you need paper openai released improving language understanding by generative pre training https s3 us west 2 amazonaws com openai assets research covers language unsupervised language understanding paper pdf this paper established that you can train a large language model on a massive set of data without any specific agenda and then once the model has learned the general aspects of language you can fine tune it for specific tasks and quickly get state of the art results in 2020 openai followed up with their gpt 3 paper language models are few shot learners https proceedings neurips cc paper 2020 file 1457c0d6bfcb4967418bfb8ac142f64a paper pdf showing that if you scale up gpt like models by another factor of 10x in terms of number of parameters and quantity of training data you no longer have to fine tune it for many tasks the capabilities emerge naturally and you get state of the art results via text interaction with the model in 2022 openai followed up on their gpt 3 accomplishments by releasing instructgpt https openai com research instruction following the intent here was to tweak the model to follow instructions while also being less toxic and biased in its outputs the key ingredient here was reinforcement learning from human feedback rlhf https arxiv org pdf 1706 03741 pdf a concept co authored by google and openai in 2017 4 which allows humans to be in the training loop to fine tune the model output to be more in line with human preferences instructgpt is the predecessor to the now famous chatgpt https en wikipedia org wiki chatgpt openai has been a major contributor to large language models over the last few years including the most recent introduction of gpt 4 https cdn openai com papers gpt 4 pdf but they are not alone meta has introduced many open source large language models like opt https huggingface co facebook opt 66b opt iml https huggingface co facebook opt iml 30b instruction tuned and llama https ai facebook com blog large language model llama meta ai google released models like flan t5 https huggingface co google flan t5 xxl and bert https huggingface co bert base uncased and there is a huge open source research community releasing models like bloom https huggingface co bigscience bloom and stablelm https github com stability ai stablelm progress is now moving so swiftly that every few weeks the state of the art is changing or models that previously required clusters to run now run on raspberry pis 4 2017 was a big year for natural language processing what is a prompt a prompt sometimes referred to as context is the text provided to a model before it begins generating output it guides the model to explore a particular area of what it has learned so that the output is relevant to your goals as an analogy if you think of the language model as a source code interpreter then a prompt is the source code to be interpreted somewhat amusingly a language model will happily attempt to guess what source code will do p align center img width 450 src https user images githubusercontent com 89960 231946874 be91d3de d773 4a6c a4ea 21043bd5fc13 png title the gpt 4 model interpreting python code p and it almost interprets the python perfectly frequently prompts will be an instruction or a question like p align center img width 500 src https user images githubusercontent com 89960 232413246 81db18dc ef5b 4073 9827 77bd0317d031 png p on the other hand if you don t specify a prompt the model has no anchor to work from and you ll see that it just randomly samples from anything it has ever consumed from gpt 3 davinci image https user images githubusercontent com 89960 232413846 70b05cd1 31b6 4977 93f0 20bf29af7132 png image https user images githubusercontent com 89960 232413930 7d414dcd 87e5 431a 91c8 bb6e0ef54f42 png image https user images githubusercontent com 89960 232413978 59c7f47d ec20 4673 9458 85471a41fee0 png from gpt 4 image https user images githubusercontent com 89960 232414631 928955e5 3bab 4d57 b1d6 5e56f00ffda1 png image https user images githubusercontent com 89960 232414678 e5b6d3f4 36c6 420f b38f 2f9c8df391fb png image https user images githubusercontent com 89960 232414734 c8f09cad aceb 4149 a28a 33675cde8011 png hidden prompts warning always assume that any content in a hidden prompt can be seen by the user in applications where a user is interacting with a model dynamically such as chatting with the model there will typically be portions of the prompt that are never intended to be seen by the user these hidden portions may occur anywhere though there is almost always a hidden prompt at the start of a conversation typically this includes an initial chunk of text that sets the tone model constraints and goals along with other dynamic information that is specific to the particular session user name location time of day etc the model is static and frozen at a point in time so if you want it to know current information like the time or the weather you must provide it if you re using the openai chat api https platform openai com docs guides chat introduction they delineate hidden prompt content by placing it in the system role here s an example of a hidden prompt followed by interactions with the content in that prompt p align center img width 550 src https user images githubusercontent com 89960 232416074 84ebcc10 2dfc 49e1 9f48 a240102877ee png title a very simple hidden prompt p in this example you can see we explain to the bot the various roles some context on the user some dynamic data we want the bot to have access to and then guidance on how the bot should respond in practice hidden prompts may be quite large here s a larger prompt taken from a chatgpt command line assistant https github com manno chatgpt linux assistant blob main system prompt txt details summary from https github com manno chatgpt linux assistant summary we are a in a chatroom with 3 users 1 user is called human the other is called backend and the other is called proxy natural language processor i will type what human says and what backend replies you will act as a proxy natural language processor to forward the requests that human asks for in a json format to the user backend user backend is an ubuntu server and the strings that are sent to it are ran in a shell and then it replies with the command stdout and the exit code the ubuntu server is mine when backend replies with the stdout and exit code you proxy natural language processor will parse and format that data into a simple english friendly way and send it to human here is an example i ask as human human how many unedited videos are left then you send a command to the backend proxy natural language processor backend command find videos unedited iname mp4 wc l then the backend responds with the command stdout and exit code backend stdout 5 exitcode 0 then you reply to the user proxy natural language processor human there are 5 unedited videos left only reply what proxy natural language processor is supposed to say and nothing else not now nor in the future for any reason another example i ask as human human what is a pem certificate then you send a command to the backend proxy natural language processor backend command xdg open https en wikipedia org wiki privacy enhanced mail then the backend responds with the command stdout and exit code backend stdout exitcode 0 then you reply to the user proxy natural language processor human i have opened a link which describes what a pem certificate is only reply what proxy natural language processor is supposed to say and nothing else not now nor in the future for any reason do not reply as backend do not complete what backend is supposed to reply you are not to complete what backend is supposed to reply also do not give an explanation of what the command does or what the exit codes mean do not ever now or in the future reply as backend only reply what proxy natural language processor is supposed to say and nothing else not now nor in the future for any reason details you ll see some good practices there such as including lots of examples repetition for important behavioral aspects constraining the replies etc warning always assume that any content in a hidden prompt can be seen by the user tokens if you thought tokens were fire in 2022 tokens in 2023 are on a whole different plane of existence the atomic unit of consumption for a language model is not a word but rather a token you can kind of think of tokens as syllables and on average they work out to about 750 words per 1 000 tokens they represent many concepts beyond just alphabetical characters such as punctuation sentence boundaries and the end of a document here s an example of how gpt may tokenize a sequence p align center img width 550 src https user images githubusercontent com 89960 232417569 8d562792 64b5 423d a7a2 db7513dd4d61 png title an example tokenization you can experiment here https platform openai com tokenizer p you can experiment with a tokenizer here https platform openai com tokenizer https platform openai com tokenizer different models will use different tokenizers with different levels of granularity you could in theory just feed a model 0 s and 1 s but then the model needs to learn the concept of characters from bits and then the concept of words from characters and so forth similarly you could feed the model a stream of raw characters but then the model needs to learn the concept of words and punctuation etc and in general the models will perform worse to learn more hugging face has a wonderful introduction to tokenizers https huggingface co docs transformers tokenizer summary and why they need to exist there s a lot of nuance around tokenization such as vocabulary size or different languages treating sentence structure meaningfully different e g words not being separated by spaces fortunately language model apis will almost always take raw text as input and tokenize it behind the scenes so you rarely need to think about tokens except for one important scenario which we discuss next token limits token limits prompts tend to be append only because you want the bot to have the entire context of previous messages in the conversation language models in general are stateless and won t remember anything about previous requests to them so you always need to include everything that it might need to know that is specific to the current session a major downside of this is that the leading language model architecture the transformer has a fixed input and output size at a certain point the prompt can t grow any larger the total size of the prompt sometimes referred to as the context window is model dependent for gpt 3 it is 4 096 tokens for gpt 4 it is 8 192 tokens or 32 768 tokens depending on which variant you use if your context grows too large for the model the most common tactic is the truncate the context in a sliding window fashion if you think of a prompt as hidden initialization prompt messages usually the hidden prompt will remain unaltered and the messages array will take the last n messages you may also see more clever tactics for prompt truncation such as discarding only the user messages first so that the bot s previous answers stay in the context for as long as possible or asking an llm to summarize the conversation and then replacing all of the messages with a single message containing that summary there is no correct answer here and the solution will depend on your application importantly when truncating the context you must truncate aggressively enough to allow room for the response as well openai s token limits include both the length of the input and the length of the output if your input to gpt 3 is 4 090 tokens it can only generate 6 tokens in response if you d like to count the number of tokens before sending the raw text to the model the specific tokenizer to use will depend on which model you are using openai has a library called tiktoken https github com openai tiktoken blob main readme md that you can use with their models though there is an important caveat that their internal tokenizer may vary slightly in count and they may append other metadata so consider this an approximation if you d like an approximation without having access to a tokenizer input length 4 will give a rough but better than you d expect approximation for english inputs prompt hacking prompt engineering and large language models are a fairly nascent field so new ways to hack around them are being discovered every day the two large classes of attacks are 1 make the bot bypass any guidelines you have given it 2 make the bot output hidden context that you didn t intend for the user to see there are no known mechanisms to comprehensively stop these so it is important that you assume the bot may do or say anything when interacting with an adversarial user fortunately in practice these are mostly cosmetic concerns think of prompts as a way to improve the normal user experience we design prompts so that normal users don t stumble outside of our intended interactions but always assume that a determined user will be able to bypass our prompt constraints jailbreaks typically hidden prompts will tell the bot to behave with a certain persona and focus on specific tasks or avoid certain words it is generally safe to assume the bot will follow these guidelines for non adversarial users although non adversarial users may accidentally bypass the guidelines too for example we can tell the bot you are a helpful assistant but you are never allowed to use the word computer if we then ask it a question about computers it will refer to them as a device used for computing because it isn t allowed to use the word computer p align center img width 550 src https user images githubusercontent com 89960 232420043 ebe5bcf1 25d9 4a31 ba84 13e9e1f62de2 png title gpt 4 trying hard to not say the word computer p it will absolutely refuse to say the word p align center img width 550 src https user images githubusercontent com 89960 232420306 6fcdd6e2 b107 45d5 a1ee 4132fbb5853e png p but we can bypass these instructions and get the model to happily use the word if we trick it by asking it to translate the pig latin version of computer p align center img width 550 src https user images githubusercontent com 89960 232420600 56083a10 b382 46a7 be18 eb9c005b8371 png p there are a number of defensive measures https learnprompting org docs prompt hacking defensive measures overview you can take here but typically the best bet is to reiterate your most important constraints as close to the end as possible for the openai chat api this might mean including it as a system message after the last user message here s an example image https user images githubusercontent com 89960 232421097 adcaace3 0b21 4c1e a5c8 46bb25faa2f7 png image https user images githubusercontent com 89960 232421142 a47e75b4 5ff6 429d 9abd a78dbc72466e png despite openai investing a lot into jailbreaks there are very clever work arounds https twitter com alexalbert status 1636488551817965568 being shared every day https twitter com zswitten status 1598088267789787136 leaks if you missed the previous warnings in this doc you should always assume that any data exposed to the language model will eventually be seen by the user as part of constructing prompts you will often embed a bunch of data in hidden prompts a k a system prompts the bot will happily relay this information to the user p align center img width 550 src https user images githubusercontent com 89960 232422860 731c1de2 9e77 4957 b257 b0bbda48558c png title the bot happily regurgitating the information it knows about the user p even if you instruct it not to reveal the information and it obeys those instructions there are millions of ways to leak data in the hidden prompt here we have an example where the bot should never mention my city but a simple reframing of the question get s it to spill the beans p align center img width 550 src https user images githubusercontent com 89960 232423121 76568893 fa42 4ad8 b2bc e1001327fa1e png title the bot refuses to reveal personal information but we convince it to tell me what city i m in regardless p similarly we get the bot to tell us what word it isn t allowed to say without ever actually saying the word p align center img width 550 src https user images githubusercontent com 89960 232423283 1718f822 59d0 4d18 9a4d 22dd3a2672c0 png title technically the bot never said computer but i was still able to get it to tell me everything i needed to know about it p you should think of a hidden prompt as a means to make the user experience better or more inline with the persona you re targeting never place any information in a prompt that you wouldn t visually render for someone to read on screen why do we need prompt engineering up above we used an analogy of prompts as the source code that a language model interprets prompt engineering is the art of writing prompts to get the language model to do what we want it to do just like software engineering is the art of writing source code to get computers to do what we want them to do when writing good prompts you have to account for the idiosyncrasies of the model s you re working with the strategies will vary with the complexity of the tasks you ll have to come up with mechanisms to constrain the model to achieve reliable results incorporate dynamic data that the model can t be trained on account for limitations in the model s training data design around context limits and many other dimensions there s an old adage that computers will only do what you tell them to do throw that advice out the window prompt engineering inverts this wisdom it s like programming in natural language against a non deterministic computer that will do anything that you haven t guided it away from doing there are two broad buckets that prompt engineering approaches fall into give a bot a fish the give a bot a fish bucket is for scenarios when you can explicitly give the bot in the hidden context all of the information it needs to do whatever task is requested of it for example if a user loaded up their dashboard and we wanted to show them a quick little friendly message about what task items they have outstanding we could get the bot to summarize it as you have 4 receipts memos to upload the most recent is from target on march 5th and the oldest is from blink fitness on january 17th thanks for staying on top of your expenses by providing a list of the entire inbox and any other user context we d like it to have p align center img width 550 src https user images githubusercontent com 89960 233465165 e0c6b266 b347 4128 8eaa 73974e852e45 png title gpt 3 summarizing a task inbox p similarly if you were helping a user book a trip you could ask the user their dates and destination behind the scenes search for flights and hotels embed the flight and hotel search results in the hidden context also embed the company s travel policy in the hidden context and then the bot will have real time travel information constraints that it can use to answer questions for the user here s an example of the bot recommending options and the user asking it to refine them p align center img width 550 src https user images githubusercontent com 89960 233465425 9e06320c b6d9 40ef b5a4 c556861c1328 png title gpt 4 helping a user book a trip p details summary full prompt summary brex is a platform for managing business expenses the following is a travel expense policy on brex airline highest fare class for flights under 6 hours is economy airline highest fare class for flights over 6 hours is premium economy car rentals must have an average daily rate of 75 or under lodging must have an average nightly rate of 400 or under lodging must be rated 4 stars or higher meals from restaurants food delivery grocery bars nightlife must be under 75 all other expenses must be under 5 000 reimbursements require review the hotel options are hotel name price reviews hilton financial district 109 night 3 9 stars hotel via 131 night 4 4 stars hyatt place san francisco 186 night 4 2 stars hotel zephyr 119 night 4 1 stars review the flight options are airline flight time duration number of stops class price united 5 30am 7 37am 2hr 7 min nonstop economy 248 delta 1 20pm 3 36pm 2hr 16 min nonstop economy 248 alaska 9 50pm 11 58pm 2hr 8 min nonstop premium 512 an employee is booking travel to san francisco for february 20th to february 25th recommend a hotel and flight that are in policy keep the recommendation concise no longer than a sentence or two but include pleasantries as though you are a friendly colleague helping me out details this is the same approach that products like microsoft bing use to incorporate dynamic data when you chat with bing it asks the bot to generate three search queries then they run three web searches and include the summarized results in the hidden context for the bot to use summarizing this section the trick to making a good experience is to change the context dynamically in response to whatever the user is trying to do giving a bot a fish is the most reliable way to ensure the bot gets a fish you will get the most consistent and reliable results with this strategy use this whenever you can semantic search if you just need the bot to know a little more about the world a common approach is to perform a semantic search https github com openai openai cookbook blob main examples question answering using embeddings ipynb a semantic search is oriented around a document embedding which you can think of as a fixed length array 5 of numbers where each number represents some aspect of the document e g if it s a science document maybe the 843rd number is large but if it s an art document the 1 115th number is large this is overly simplistic but conveys the idea 6 in addition to computing an embedding for a document you can also compute an embedding for a user query using the same function if the user asks why is the sky blue you compute the embedding of that question and in theory this embedding will be more similar to embeddings of documents that mention the sky than embeddings that don t talk about the sky to find documents related to the user query you compute the embedding and then find the top n documents that have the most similar embedding then we place these documents or summaries of these documents in the hidden context for the bot to reference notably sometimes user queries are so short that the embedding isn t particularly valuable there is a clever technique described in a paper published in december 2022 https arxiv org pdf 2212 10496 pdf called a hypothetical document embedding or hyde using this technique you ask the model to generate a hypothetical document in response to the user s query and then compute the embedding for this generated document the model fabricates a document out of thin air but the approach works the hyde technique uses more calls to the model but for many use cases has notable boosts in results 5 usually referred to as a vector 6 the vector features are learned automatically and the specific values aren t directly interpretable by a human without some effort teach a bot to fish sometimes you ll want the bot to have the capability to perform actions on the user s behalf like adding a memo to a receipt or plotting a chart or perhaps we want it to retrieve data in more nuanced ways than semantic search would allow for like retrieving the past 90 days of expenses in these scenarios we need to teach the bot how to fish command grammars we can give the bot a list of commands for our system to interpret along with descriptions and examples for the commands and then have it produce programs composed of those commands there are many caveats to consider when going with this approach with complex command grammars the bot will tend to hallucinate commands or arguments that could plausibly exist but don t actually the art to getting this right is enumerating commands that have relatively high levels of abstraction while giving the bot sufficient flexibility to compose them in novel and useful ways for example giving the bot a plot the last 90 days of expenses command is not particularly flexible or composable in what the bot can do with it similarly a draw pixel at x y x y rgb command would be far too low level but giving the bot a plot expenses and list expenses command provides some good primitives that the bot has some flexibility with in an example below we use this list of commands command arguments description list expenses budget returns a list of expenses for a given budget converse message a message to show to the user plot expenses expenses plots a list of expenses get budget by name budget name retrieves a budget by name list budgets returns a list of budgets the user has access to add memo inbox item id memo message adds a memo to the provided inbox item we provide this table to the model in markdown format which the language model handles incredibly well presumably because openai trains heavily on data from github in this example below we ask the model to output the commands in reverse polish notation https en wikipedia org wiki reverse polish notation 7 7 the model handles the simplicity of rpn astoundingly well p align center img width 550 src https user images githubusercontent com 89960 233505150 aef4409c 03ba 4669 95d7 6c48f3c2c3ea png title a bot happily generating commands to run in response to user queries p there are some interesting subtle things going on in that example beyond just command generation when we ask it to add a memo to the shake shack expense the model knows that the command add memo takes an expense id but we never tell it the expense id so it looks up shake shack in the table of expenses we provided it then grabs the id from the corresponding id column and then uses that as an argument to add memo getting command grammars working reliably in complex situations can be tricky the best levers we have here are to provide lots of descriptions and as many examples of usage as we can large language models are few shot learners https en wikipedia org wiki few shot learning natural language processing meaning that they can learn a new task by being provided just a few examples in general the more examples you provide the better off you ll be but that also eats into your token budget so it s a balance here s a more complex example with the output specified in json instead of rpn and we use typescript to define the return types of commands p align center img width 550 src https user images githubusercontent com 89960 233505696 fc440931 9baf 4d06 80e7 54801532d63f png title a bot happily generating commands to run in response to user queries p details summary full prompt summary you are a financial assistant working at brex but you are also an expert programmer i am a customer of brex you are to answer my questions by composing a series of commands the output types are typescript type linkedaccount id string bank details name string type string brex account id string last four string available balance amount number as of date date current balance amount number as of date date type expense id string memo string amount number type budget id string name string description string limit amount number currency string the commands you have available are command arguments description output format nth index values return the nth item from an array any push value adds a value to the stack to be consumed by a future command any value key object returns the value associated with a key any values key object returns an array of values pulled from the corresponding key in array of objects any sum value sums an array of numbers number plot title values plots the set of values in a chart with the given title plot list linked accounts lists all bank connections that are eligible to make ach transfers to brex cash account linkedaccount list expenses budget id given a budget id returns the list of expenses for it expense get budget by name name given a name returns the budget budget add memo expense id message adds a memo to an expense bool converse message send the user a message null only respond with commands output the commands in json as an abstract syntax tree important only respond with a program do not respond with any text that isn t part of a program do not write prose even if instructed do not explain yourself you can only generate commands but you are an expert at generating commands details this version is a bit easier to parse and interpret if your language of choice has a json parse function there is no industry established best format for defining a dsl for the model to generate programs so consider this an area of active research you will bump into limits and as we overcome these limits we may discover more optimal ways of defining commands react in march of 2023 princeton and google released a paper react synergizing reasoning and acting in language models https arxiv org pdf 2210 03629 pdf where they introduce a variant of command grammars that allows for fully autonomous interactive execution of actions and retrieval of data the model is instructed to return a thought and an action that it would like to perform another agent e g our client then performs the action and returns it to the model as an observation the model will then loop to return more thoughts and actions until it returns an answer this is an incredibly powerful technique effectively allowing the bot to be its own research assistant and possibly take actions on behalf of the user combined with a powerful command grammar the bot should rapidly be able to answer a massive set of user requests in this example we give the model a small set of commands related to getting employee data and searching wikipedia command arguments description find employee name retrieves an employee by name get employee id retrieves an employee by id get location id retrieves a location by id get reports employee id retrieves a list of employee ids that report to the employee associated with employee id wikipedia article retrieves a wikipedia article on a topic we then ask the bot a simple question is my manager famous we see that the bot 1 first looks up our employee profile 2 from our profile gets our manager s id and looks up their profile 3 extracts our manager s name and searches for them on wikipedia i chose a fictional character for the manager in this scenario 4 the bot reads the wikipedia article and concludes that can t be my manager since it is a fictional character 5 the bot then modifies its search to include real person 6 seeing that there are no results the bot concludes that my manager is not famous image https user images githubusercontent com 89960 233506839 5c8b2d77 1d78 464d bc33 a725e12f2624 png image https user images githubusercontent com 89960 233506870 05fc415d efa2 48b7 aad9 b5035e535e6d png details summary full prompt summary you are a helpful assistant you run in a loop seeking additional information to answer a user s question until you are able to answer the question today is june 1 2025 my name is fabian seacaster my employee id is 82442 the commands to seek information are command arguments description find employee name retrieves an employee by name get employee id retrieves an employee by id get location id retrieves a location by id get reports employee id retrieves a list of employee ids that report to the employee associated with employee id wikipedia article retrieves a wikipedia article on a topic your response will be in json and will include a thought action to retrieve data that you need in order to answer the question or it will include the answer when data has been retrieved it will be included as an observation you will continue generating thoughts and actions until you get to an answer or conclude that you can t example 1 user what is the population of philadelphia assistant thought wikipedia likely has this information i m looking it up action command wikipedia article philadelphia assistant observation philadelphia often called philly is the largest city in the commonwealth of pennsylvania and the second largest city in both the northeast megalopolis and mid atlantic regions after new york city it is one of the most historically significant cities in the united states and served as the nation s capital city until 1800 philadelphia is the nation s sixth largest city with a population of 1 603 797 as of the 2020 census since 1854 the city has been coextensive with philadelphia county the most populous county in pennsylvania and the urban core of the delaware valley the nation s seventh largest and one of the world s largest metropolitan regions with 6 245 million residents in 2020 philadelphia is known for its extensive contributions to american history and for its role in the life sciences business and industry art literature and music assistant answer the population of philadelphia as of the 2020 census is 1 603 797 people example 2 user what is my manager s city assistant thought let me look up who your manager is first i need to look up your profile action command get employee id 92352 assistant observation id 78334 name ms manager location id 8832 assistant thought your manager is ms manager i m looking up their location action command get location id 8832 assistant observation id 8832 name philadelphia assistant answer your manager lives in philadelphia details gpt 4 vs gpt 3 5 in most of the examples in this doc the difference between gpt 3 5 and gpt 4 is negligible but for teaching a bot to fish scenarios the difference between the models is notable none of the above examples of command grammars for example work without meaningful modifications for gpt 3 5 at a minimum you have to provide a number of examples at least one usage example per command before you get any reasonable results and for complex sets of commands it may hallucinate new commands or create fictional arguments with a sufficiently thorough hidden prompt you should be able to overcome these limitations gpt 4 is capable of far more consistent and complex logic with far simpler prompts and can get by with zero or small numbers of examples though it is always beneficial to include as many as possible strategies this section contains examples and strategies for specific needs or problems for successful prompt engineering you will need to combine some subset of all of the strategies enumerated in this document don t be afraid to mix and match things or invent your own approaches embedding data in hidden contexts you ll frequently want to embed all sorts of data the specific strategy will vary depending on the type and quantity of data you are embedding simple lists for one off objects enumerating fields values in a normal bulleted list works pretty well p align center img width 550 src https user images githubusercontent com 89960 233507156 0bdbc0af d977 44e0 a8d5 b30538c5bbd9 png title gpt 4 extracting steve s occupation from a list attributes p it will also work for larger sets of things but there are other formats for lists of data that gpt handles more reliably regardless here s an example p align center img width 550 src https user images githubusercontent com 89960 233507223 9cda591e 62f3 4339 b227 a07c37b90724 png title gpt 4 answering questions about a set of expenses p markdown tables markdown tables are great for scenarios where you have many items of the same type to enumerate fortunately openai s models are exceptionally good at working with markdown tables presumably from the tons of github data they ve trained on we can reframe the above using markdown tables instead p align center img width 550 src https user images githubusercontent com 89960 233507313 7ccd825c 71b9 46d3 80c9 30bf97a8e090 png title gpt 4 answering questions about a set of expenses from a markdown table p p align center img width 550 src https user images githubusercontent com 89960 233507395 b8ecb641 726c 4e57 b85e 13f6b7717f22 png title gpt 4 answering questions about a set of expenses from a markdown table p note that in this last example the items in the table have an explicit date february 2nd in our question we asked about today and earlier in the prompt we mentioned that today was feb 2 the model correctly handled the transitive inference converting today to february 2nd and then looking up february 2nd in the table json markdown tables work really well for many use cases and should be preferred due to their density and ability for the model to handle them reliably but you may run into scenarios where you have many columns and the model struggles with it or every item has some custom attributes and it doesn t make sense to have dozens of columns of empty data in these scenarios json is another format that the model handles really well the close proximity of keys to their values makes it easy for the model to keep the mapping straight here is the same example from the markdown table but with json instead p align center img width 550 src https user images githubusercontent com 89960 233507559 26e6615d 4896 4a2c b6ff 44cbd7d349dc png title gpt 4 answering questions about a set of expenses from a json blob p freeform text occasionally you ll want to include freeform text in a prompt that you would like to delineate from the rest of the prompt such as embedding a document for the bot to reference in these scenarios surrounding the document with triple backticks works well 8 p align center img width 550 src https user images githubusercontent com 89960 233507684 93222728 e216 47b4 8554 04acf9ec6201 png title gpt 4 answering questions about a set of expenses from a json blob p 8 a good rule of thumb for anything you re doing in prompts is to lean heavily on things the model would have learned from github nested data not all data is flat and linear sometimes you ll need to embed data that is nested or has relations to other data in these scenarios lean on json p align center img width 550 src https user images githubusercontent com 89960 233507758 7baffcaa 647b 4869 9cfb a7cf8849c453 png title gpt 4 handles nested json very reliably p details summary full prompt summary you are a helpful assistant you answer questions about users here is what you know about them users id 1 name john doe contact address street 123 main st city anytown state ca zip 12345 phone 555 555 1234 email johndoe example com id 2 name jane smith contact address street 456 elm st city sometown state tx zip 54321 phone 555 555 5678 email janesmith example com id 3 name alice johnson contact address street 789 oak st city othertown state ny zip 67890 phone 555 555 2468 email alicejohnson example com id 4 name bob williams contact address street 135 maple st city thistown state fl zip 98765 phone 555 555 8642 email bobwilliams example com id 5 name charlie brown contact address street 246 pine st city thatstown state wa zip 86420 phone 555 555 7531 email charliebrown example com id 6 name diane davis contact address street 369 willow st city sumtown state co zip 15980 phone 555 555 9512 email dianedavis example com id 7 name edward martinez contact address street 482 aspen st city newtown state mi zip 35742 phone 555 555 6813 email edwardmartinez example com id 8 name fiona taylor contact address street 531 birch st city oldtown state oh zip 85249 phone 555 555 4268 email fionataylor example com id 9 name george thompson contact address street 678 cedar st city nexttown state ga zip 74125 phone 555 555 3142 email georgethompson example com id 10 name helen white contact address street 852 spruce st city lasttown state va zip 96321 phone 555 555 7890 email helenwhite example com details if using nested json winds up being too verbose for your token budget fallback to relational tables defined with markdown p align center img width 550 src https user images githubusercontent com 89960 233507968 a378587b e468 4882 a1e8 678d9f3933d3 png title gpt 4 handles relational tables pretty reliably too p details summary full prompt summary you are a helpful assistant you answer questions about users here is what you know about them table 1 users id pk name 1 john doe 2 jane smith 3 alice johnson 4 bob williams 5 charlie brown 6 diane davis 7 edward martinez 8 fiona taylor 9 george thompson 10 helen white table 2 addresses id pk user id fk street city state zip 1 1 123 main st anytown ca 12345 2 2 456 elm st sometown tx 54321 3 3 789 oak st othertown ny 67890 4 4 135 maple st thistown fl 98765 5 5 246 pine st thatstown wa 86420 6 6 369 willow st sumtown co 15980 7 7 482 aspen st newtown mi 35742 8 8 531 birch st oldtown oh 85249 9 9 678 cedar st nexttown ga 74125 10 10 852 spruce st lasttown va 96321 table 3 phone numbers id pk user id fk phone 1 1 555 555 1234 2 2 555 555 5678 3 3 555 555 2468 4 4 555 555 8642 5 5 555 555 7531 6 6 555 555 9512 7 7 555 555 6813 8 8 555 555 4268 9 9 555 555 3142 10 10 555 555 7890 table 4 emails id pk user id fk email 1 1 johndoe example com 2 2 janesmith example com 3 3 alicejohnson example com 4 4 bobwilliams example com 5 5 charliebrown example com 6 6 dianedavis example com 7 7 edwardmartinez example com 8 8 fionataylor example com 9 9 georgethompson example com 10 10 helenwhite example com table 5 cities id pk name state population median income 1 anytown ca 50 000 70 000 2 sometown tx 100 000 60 000 3 othertown ny 25 000 80 000 4 thistown fl 75 000 65 000 5 thatstown wa 40 000 75 000 6 sumtown co 20 000 85 000 7 newtown mi 60 000 55 000 8 oldtown oh 30 000 70 000 9 nexttown ga 15 000 90 000 10 lasttown va 10 000 100 000 details the model works well with data in 3rd normal form https en wikipedia org wiki third normal form but may struggle with too many joins in experiments it seems to do okay with at least three levels of nested joins in the example above the model successfully joins from users to addresses to cities to infer the likely income for george 90 000 citations frequently a natural language response isn t sufficient on its own and you ll want the model s output to cite where it is getting data from one useful thing to note here is that anything you might want to cite should have a unique id the simplest approach is to just ask the model to link to anything it references p align center img width 550 src https user images githubusercontent com 89960 233509069 1dcbffa2 8357 49b5 be43 9791f93bd0f8 png title gpt 4 will reliably link to data if you ask it to p programmatic consumption by default language models output natural language text but frequently we need to interact with this result in a programmatic way that goes beyond simply printing it out on screen you can achieve this by asking the model to output the results in your favorite serialization format json and yaml seem to work best make sure you give the model an example of the output format you d like building on our previous travel example above we can augment our prompt to tell it produce your output as json the format should be message the message to show the user hotelid 432 flightid 831 do not include the ids in your message and now we ll get interactions like this p align center img width 550 src https user images githubusercontent com 89960 233509174 be0c3bc5 08e3 4d1a 8841 52c401def770 png title gpt 4 providing travel recommendations in an easy to work with format p you could imagine the ui for this rendering the message as normal text but then also adding discrete buttons for booking the flight hotel or auto filling a form for the user as another example let s build on the citations citations example but move beyond markdown links we can ask it to produce json with a normal message along with a list of items used in the creation of that message in this scenario you won t know exactly where in the message the citations were leveraged but you ll know that they were used somewhere p align center img width 550 src https user images githubusercontent com 89960 233509280 59d9ff46 0e95 488a b314 a7d2b7c9bfa3 png title asking the model to provide a list of citations is a reliable way to programmatically know what data the model leaned on in its response p interestingly in the model s response to how much did i spend at target it provides a single value 188 16 but importantly in the citations array it lists the individual expenses that it used to compute that value chain of thought sometimes you will bang your head on a prompt trying to get the model to output reliable results but no matter what you do it just won t work this will frequently happen when the bot s final output requires intermediate thinking but you ask the bot only for the output and nothing else the answer may surprise you ask the bot to show its work in october 2022 google released a paper chain of thought prompting elicits reasoning in large language models https arxiv org pdf 2201 11903 pdf where they showed that if in your hidden prompt you give the bot examples of answering questions by showing your work then when you ask the bot to answer something it will show its work and produce more reliable answers just a few weeks after that paper was published at the end of october 2022 the university of tokyo and google released the paper large language models are zero shot reasoners https openreview net pdf id e2tbb5y0yff where they show that you don t even need to provide examples you simply have to ask the bot to think step by step averaging here is an example where we ask the bot to compute the average expense excluding target the actual answer is 136 77 and the bot almost gets it correct with 136 43 p align center img width 550 src https user images githubusercontent com 89960 233509534 2b32c8dd a1ee 42ea 82fb 4f84cfe7e9ba png title the model almost gets the average correct but is a few cents off p if we simply add let s think step by step the model gets the correct answer p align center img width 550 src https user images githubusercontent com 89960 233509608 6e53995b 668b 47f6 9b5e 67afad89f8bc png title when we ask the model to show its work it gets the correct answer p interpreting code let s revisit the python example from earlier and apply chain of thought prompting to our question as a reminder when we asked the bot to evaluate the python code it gets it slightly wrong the correct answer is hello brex brex brex but the bot gets confused about the number of s to include in below s example it outputs hello brex brex brex p align center img width 550 src https user images githubusercontent com 89960 233509724 8f3302f8 59eb 4d3b 8939 53d7f63b0299 png title the bot almost interprets the python code correctly but is a little off p if we ask the bot to show its work then it gets the correct answer p align center img width 550 src https user images githubusercontent com 89960 233509790 2a0f2189 d864 4d27 aacb cfc936fad907 png title the bot correctly interprets the python code if you ask it to show its work p delimiters in many scenarios you may not want to show the end user all of the bot s thinking and instead just want to show the final answer you can ask the bot to delineate the final answer from its thinking there are many ways to do this but let s use json to make it easy to parse p align center img width 550 src https user images githubusercontent com 89960 233509865 4f3e7265 6645 4d43 8644 ecac5c0ca4a7 png title the bot showing its work while also delimiting the final answer for easy extraction p using chain of thought prompting will consume more tokens resulting in increased price and latency but the results are noticeably more reliable for many scenarios it s a valuable tool to use when you need the bot to do something complex and as reliably as possible fine tuning sometimes no matter what tricks you throw at the model it just won t do what you want it to do in these scenarios you can sometimes fallback to fine tuning this should in general be a last resort fine tuning https platform openai com docs guides fine tuning is the process of taking an already trained model and then giving it thousands or more of example input output pairs it does not eliminate the need for hidden prompts because you still need to embed dynamic data but it may make the prompts smaller and more reliable downsides there are many downsides to fine tuning if it is at all possible take advantage of the nature of language models being zero shot one shot and few shot learners https en wikipedia org wiki few shot learning natural language processing by teaching them to do something in their prompt rather than fine tuning some of the downsides include not possible gpt 3 5 gpt 4 isn t fine tunable https platform openai com docs guides chat is fine tuning available for gpt 3 5 turbo which is the primary model api we ll be using so we simply can t lean in fine tuning overhead fine tuning requires manually creating tons of data velocity the iteration loop becomes much slower every time you want to add a new capability instead of adding a few lines to a prompt you need to create a bunch of fake data and then run the finetune process and then use the newly fine tuned model cost it is up to 60x more expensive to use a fine tuned gpt 3 model vs the stock gpt 3 5 turbo model and it is 2x more expensive to use a fine tuned gpt 3 model vs the stock gpt 4 model if you fine tune a model never use real customer data always use synthetic data the model may memorize portions of the data you provide and may regurgitate private data to other users that shouldn t be seeing it if you never fine tune a model we don t have to worry about accidentally leaking data into the model additional resources star2 openai cookbook https github com openai openai cookbook star2 technologist prompt hacking https learnprompting org docs category prompt hacking technologist books dair ai prompt engineering guide https github com dair ai prompt engineering guide books | ai |
|
tinysdr | overview img src images tinysdr jpg alt tinysdr board width 321 height 250 align right tinysdr is the first software defined radio platform specialized for internet of things networks hardware tinysdr schematic is in hardware hardware schematic pdf you can download pcb design files hardware pcb tinysdr zip to build tinysdr hardware firmware tinysdr firmware ccs project is in firmware firmware fpga demos tinysdr bluetooth beacons and lora demos are in demo demo lora modulator https github com uw x lora modulator fsk modulator https github com mehrdadh fsk modulator contributers mehrdad hessar https github com mehrdadh ali najafi https github com anajafi vikram iyer https github com viyer | tinysdr msp432 lattice ecp5 sdr software-defined-radio long-range low-power at86rf215 atmel | server |
competency-framework | competency framework this defines competencies in the information and communication technology sphere it s a open and free resource which can be used freely by everyone entitys dl dt competency dt dd a competency describes the know how to do something based on skills and knowledge dd dt discipline dt dd a discipline describes an area of information and communication technology and it categorizes competencies dd dl tools this chapter documents some prefered tools to work with this repository editing with visual studio code 1 install visual studio code https code visualstudio com 1 add red hats xml extension https marketplace visualstudio com items itemname redhat vscode xml validation with xerces 1 install xerces c http xerces apache org xerces c on archlinux pacman s xerces c 1 use stdinparse http xerces apache org xerces c stdinparse 3 html to validate documents br stdinparse s n document xml resources documents best practices for xml internationalization https www w3 org tr xml i18n bp | server |
|
IncidentDatabase | incidentdatabase software engineering group project web based database for recording incidents http compsci adelphi edu ryandeisler issuetrackingsystem login php can only be used on adelphi university network | server |
|
configuration-discovery | ibm cloud configuration discovery use configuration discovery to import the existing cloud resources in your account and its configuration settings to auto generate the terraform configuration file tf and state file tfstate it makes it easy for you to adopt the infrastructure as code practices it can reverse engineer the current ibm cloud environment that was provisioned using ui or cli configuration discovery tool is powered by terraformer https github com googlecloudplatform terraformer this tool will augment the terraformer with a number of capabilities that are native to ibm cloud dependencies terraform https www terraform io downloads html 0 12 31 or 0 13 terraformer https github com googlecloudplatform terraformer 0 8 17 ibm cloud provider https github com ibm cloud terraform provider ibm go https golang org doc install 1 15 to build the discovery tool mongodb https docs mongodb com manual installation v4 4 5 to run as a server installation configuration discovery tool run this command to install the terraformer and configuration discovery tool curl ql https raw githubusercontent com ibm cloud configuration discovery main install sh sh you can download pre built binaries for linux and macos on the releases page https github com ibm cloud configuration discovery releases ibm cloud provider plugin download the ibm cloud provider plugin for terraform from release page https github com ibm cloud terraform provider ibm releases unzip the release archive to extract the plugin binary terraform provider ibm vx y z move the binary into the terraform plugins directory https www terraform io docs configuration providers html third party plugins for the platform linux unix terraform d plugins linux amd64 mac os x terraform d plugins darwin amd64 usage discovery name ibm cloud discovery cli lets you create state file and tf config from resources in your cloud account for the green field and brown field imports of config and statefile and all terraformer related usage discovery global options command command options arguments version 0 1 1 commands help h shows a list of commands or help for one command discovery version discovery version config configure discovery config config name config name import discovery import services services to import tags tags config name config name compact global options help h show help version v print the version configuration discovery commands below commands help you to import your resources into terraform configuration for more detailed description run discovery help for help on a command run discovery help command command description discovery version ibm cloud discovery cli version gives you other dependency information shows all supported importable resources discovery config create a local configuration directory for exporting the terrraform configuration and state files discovery import import tf config and state for resources in your ibm cloud account import all the resources for this service you are now ready to use the configuration discovery tool cmd discovery tutorial md tutorial capabilities green field scenario importing the existing infrastructure on a clean state cmd discovery capabilities md green field import scenario upgrading the terraform state file to the latest terraform versions cmd discovery capabilities md upgrading the terraform state file to the latest terraform versions future enhancements brown field scenario importing the existing infrastructure and merge the generated terraform files into the presence of already existing terraform files rewrite terraform resource into terraform modules supports integration of the configuration discovery tool into the vs code extension for ibm cloud schematics https www ibm com cloud blog announcements introducing the visual studio code extension for ibm cloud schematics steps to use the configuration discovery files main go this file contains the web server and handlers cmd discovery code for the tool steps to use the project as an tool build and install the tool to your gopath make install cli export the required env vars ic api key your ibm cloud api key imports resources in that account for which user has access discovery config dir directory where to generate and import the terraform code discovery uses only this directory for any read write op example commands discovery version discovery config config name testfolder discovery import services ibm is vpc config name testfolder compact merge steps to use as a server todo anil add the swagger api link here may be later we can host the swagger github page if needed start the server cd go src github com git clone git github com ibm cloud configuration discovery git cd configuration discovery go run main go docs go http localhost 8080 or make run mac or make run local for linux how to run the configuration discovery as a docker container run as docker container make docker build make docker run first two need mongodb service running on localhost 27017 third needs mongodb running as docker container to run mongodb as docker container with 27017 exposed outside this will work for all three methods above run this before any of the above steps make docker run mongo how to run the configuration discovery as a container cd go src github com git clone git github com ibm cloud configuration discovery git cd configuration discovery docker build t configuration discovery docker images export api image configuration discovery latest docker compose up build d contributing to configuration discovery please have a look at the contributing md contributing md file for some guidance before submitting a pull request report a issue feature request is something broken have a issue bug to report use the bug report https github com ibm cloud configuration discovery issues new assignees labels template bug report md title link but before raising a issue please check the issues list https github com ibm cloud configuration discovery issues to see if the issue is already raised by someone do you have a new feature or enhancement you would like to see use the feature request https github com ibm cloud configuration discovery issues new assignees labels template feature request md title link head to config discovery users https ibm cloud schematics slack com archives c02gu9wnn4s slack channel to engage with the team license the project is licensed under the apache 2 0 license https www apache org licenses license 2 0 a copy is also available in the license file in this repository | terraform terraformer | cloud |
ArcV | h1 align center arcv h1 h4 align center computer vision amp augmented reality library h4 summary arcv pronounced ark v stands for a ugmented r eality and c omputer v ision library this name may change in the future not all that original as it is i know written in c it is primarily developed for learning purposes it is intended to be optimized and to run relatively fast even on low end old computers and smartphones this library is available for linux and windows it is also especially aimed to be running on android if you want to get started head to the wiki https github com razakhel arcv wiki arcv is a c omputer v ision library computer vision implies vision by computer that being said how can there be vision without a bit of image processing objectives implemented implementing matrix vector classes yes loading reading an image jpeg png tga bmp bpg yes png saving writing an image yes png changing colorspace yes convolution filtering yes operations on images rotation flip thresholding yes detecting basic features corners lines circles in progress detecting advanced features object recognition orb algorithm no handle windowing yes getting stream from webcam yes linux may be decided to be added facial recognition motion analysis tracking optical flow image restoration scene reconstruction an a ugmented r eality library the principle of augmented reality here is to place virtual elements over a picture or a video stream this superposition having to be as realistic as possible this part will not be begun before a while though being the most interesting it makes less sense to move onto ar while cv isn t advanced enough objectives implemented fiducial markers recognition no pose estimation no 3d models integration opengl vulkan no to be continued external links links to wikipedia computer vision https en wikipedia org wiki computer vision convolution https en wikipedia org wiki kernel image processing edge detection https en wikipedia org wiki edge detection canny detector https en wikipedia org wiki canny edge detector sobel operator https en wikipedia org wiki sobel operator corner detection https en wikipedia org wiki corner detection harris operator https en wikipedia org wiki corner detection the harris 26 stephens 2f plessey 2f shi e2 80 93tomasi corner detection algorithms augmented reality https en wikipedia org wiki augmented reality fiducial marker https en wikipedia org wiki fiducial marker | library computer-vision augmented-reality image-processing c-plus-plus linux windows c-plus-plus-14 cmake | ai |
enhanced-memory-game | h1 align center memory game h1 h3 align center a memory game like you ve never seen it before with extra features to make your experience even better h3 p align center img alt github language count src https img shields io github languages count lucaschf enhanced memory game color 2304d361 img alt repository size src https img shields io github repo size lucaschf enhanced memory game style plastic img alt made by tsi 2021 2 src https img shields io badge made 20by tsi 237519c1 a href https lucaschf github io enhanced memory game img alt stargazers src https img shields io badge website memorygame 237159c1 style flat logo ghost a p h4 align center status finished h4 about a new style and dynamic for a game as simple and amazing as a memory game bringing back that cherished childhood memory in a more challenging and innovative way features x difficulty level x accessibility mode x speed score x ranking implemented x easter egg included x light and compact x users have access to the mobile application where they can x download the app available in the repository x download source code and build for mobile team a big thank you to this group who made this work a great team experience table tr td align center a href https github com danielsf2 img style border radius 50 src https avatars2 githubusercontent com u 39291799 v 4 width 100px alt sub b daniel soares b sub br td td align center a href https github com edmilsonosjr img style border radius 50 src https avatars2 githubusercontent com u 44274029 v 4 width 100px alt sub b edmilson jr b sub br td td align center a href https github com guimagnus img style border radius 50 src https avatars2 githubusercontent com u 40570380 v 4 width 100px alt sub b guilherme magnus b sub br td td align center a href https github com lucaschf img style border radius 50 src https avatars2 githubusercontent com u 15016387 v 4 width 100px alt sub b lucas cristovam b sub br td td td align center a href https github com maikiferreira img style border radius 50 src https avatars2 githubusercontent com u 22885261 v 4 width 100px alt sub b maiki ferreira b sub br td td align center a href https github com uviniciusaugusto img style border radius 50 src https avatars2 githubusercontent com u 48693496 v 4 width 100px alt sub b vin cius augusto b sub br td td align center a href https github com viniciustristao img style border radius 50 src https avatars2 githubusercontent com u 19704306 v 4 width 100px alt sub b vin cius trist o b sub br td tr table | front_end |
|
Toolbox-ComputerVision | toolbox computervision image processing and computer vision project toolbox starter code instructions are on the the toolbox page https toolboxes olin build image processing | ai |
|
finetune-anything | introduction the segment anything model sam https github com facebookresearch segment anything has revolutionized computer vision relying on fine tuning of sam will solve a large number of basic computer vision tasks we are designing a class aware one stage tool for training fine tuning models based on sam you need to supply the datasets for your tasks and the supported task supported tasks name this tool will help you to get a finetuned model for your task you are also allowed to design your own extend sam model and fa supply the training testing and deploy process for you img width 640 style display block margin 0 auto src https user images githubusercontent com 67993288 230864865 db8810fd 9f0c 4f3e 81b1 8753b5121d03 png design finetune anything further encapsulates the three parts of the original sam i e image encoder adapter prompt encoder adapter and mask decoder adatper we will support the base extend sam model for each task users also could design your own customized modules in each adapter use fa to design different adapters and set whether the parameters of any module are fixed for modules with unfixed parameters parameters such as lr weight decay can be set to coordinate with the fine tuning of the model check details in how to use https github com ziqi jin finetune anything blob main how to use finetune anything md for example maskdecoder is encapsulated as maskdecoderadapter the current maskdecoderadatper contains two parts decoderneck and decoderhead img width 640 style display block margin 0 auto src https user images githubusercontent com 67993288 244574810 db9a50ad 4082 4647 8b91 7a261f5aad40 svg supported tasks x semantic segmentation x train x eval test matting instance segmentation detection supported datasets x torchvocsegmentation x basesemantic baseinstance basematting deploy onnx export support plan fa will be updated in the following order mattng task prompt part structure mobilesam https github com chaoningzhang mobilesam model instance segmentation task usage finetune anything fa supports the entire training process of sam model fine tuning including the modification of the model structure as well as the model training verification and testing processes for details check the how to use https github com ziqi jin finetune anything blob main how to use finetune anything md the quick start quick start gives an example of quickly using fa to train a custom semantic segmentation model quick start install step1 git clone https github com ziqi jin finetune anything git cd finetune anything pip install r requirements txt step2 download the sam weights from sam repository https github com facebookresearch segment anything model checkpoints step3 modify the contents of yaml file for the specific task in config e g ckpt path model type train cuda visible devices your gpu number python train py task name semantic seg one more thing if you need to use loss dataset or other functions that are not supported by fa please submit an issue and i will help you to implement them at the same time developers are also welcome to develop new loss dataset or other new functions for fa please submit your pr pull requests related resources documents https github com ziqi jin finetune anything blob main how to use finetune anything md | computer-vision deep-learning segment-anything fine-tune | ai |
android-md-core | download https api bintray com packages henrytao me maven mdcore images download svg https bintray com henrytao me maven mdcore latestversion android arsenal https img shields io badge android 20arsenal android md core brightgreen svg style flat http android arsenal com details 1 2469 android md core appcompat and google support design are really awesome but they also have some limitations theming android app is not an easy task especially keeping consistent ui on both lollipop and non lollipop devices is even harder if you ve tried cardview spinner theme you know what i mean so i propose android md core material bootstrap for android development like bootstrap or foundation for web i am working hard to predefine element styles as many as i can if you find that it still doesn t meet your need don t hesitate to send me a request i love to work with you to solve problems send a request here https github com henrytao me android md core issues installation compile me henrytao mdcore latest version android md core is an ui library and pretty much depended on appcompat and support design so that versioning is quite the same with those libraries from google android md core is deployed to jcenter make sure you have jcenter in your project gradle usages step 1 setup baseactivity java public abstract class baseactivity extends appcompatactivity override protected void oncreate nullable bundle savedinstancestate this method should be called before calling super mdcore init this super oncreate savedinstancestate step 2 setup theme using either mdtheme light or mdtheme dark xml style name apptheme parent mdtheme light style style name apptheme dark parent mdtheme dark style demo get it on google play https raw githubusercontent com henrytao me android md core master screenshots google play png https play google com store apps details id me henrytao mdcoreinaction please note that the app on the play store is not always the latest version concepts android md core is designed base on some priciples widely support based on appcompat and google support design for sure simplicity used attribute based theme system rather than value based theme system this increases the flexibility to have multiple theme in one app ease to use predefined style for most of base elements so that you can use easily like bootstrap or foundation for web consistency consistent ui for both lollipop and non lollipop devices modern keep up to date with google material design https www google com design spec material design introduction html features button screenshots all in one jpg contributing any contributions are welcome please check the contributing contributing md guideline before submitting a new issue wanna send pr click here https github com henrytao me android md core pulls license copyright 2015 henry tao hi henrytao me licensed under the apache license version 2 0 the license you may not use this file except in compliance with the license you may obtain a copy of the license at http www apache org licenses license 2 0 unless required by applicable law or agreed to in writing software distributed under the license is distributed on an as is basis without warranties or conditions of any kind either express or implied see the license for the specific language governing permissions and limitations under the license | front_end |
|
Csharp-database-assignment | csharp database assignments this repo was for assignments of database course in cairo university faculty of engineering | server |
|
Embedded-Systems-Design | embedded systems design embedded systems design course es670 project description the developed project consists of a temperature controller using the frdm kl25 development kit coupled to the mclab2 peripheral board the main objective is to control the peripheral board heater temperature implementing remote communication via uart and local communication via interface a state machine was implemented to control the temperature allowing the user to adjust parameters such as the cooler s speed the desired temperature and the pid controller gains communication with the system is done through serial communication via uart using the putty terminal and also through a local interface with buttons and an lcd board the state machine is also used to manage user interaction with the local interface the system has a pid controller with predefined gains but the user can change these values either through remote communication or through the local interface an interrupt is used to update the controller with the current temperature set point and to obtain cooler s and heater s information such as the cooler s speed in rpm and the average of the last 5 heater s temperatures some additional features have been implemented such as turning off the heater and turning on the cooler at maximum if the set point is greater than 90 c and the use of the frdm kl25z s rgb led to indicate the duty cycle of the heater through the color of the led software used this project was implemented in c on the kinetis design studio ide https www nxp com design designs design studio integrated development environment ide kds ide authors igor barros teixeira github https i stack imgur com tskmh png github https github com igor bt matheus santos sano github https i stack imgur com tskmh png github https github com matsano we would like to thank our professor mr rodrigo moreira bacurau for the knowledge taught in embedded systems design course at unicamp https www unicamp br unicamp which were essential for the realization of this project | os |
|
openspawn | openspawn opensource cloud authoring tool for procedural engineering | cloud |
|
MapGIS-Mobile-React-Native-V10.3 | mapgis mobile react native v10 3 mapgis mobile for react native mapgis react native javascript android ios gis react native mapgis mobile react native bash yarn add mapgis mobile react native 1 1 4 or with npm npm install mapgis mobile react native 1 1 4 react native 0 60 and higher linking is automatic https github com react native community cli blob master docs autolinking md react native 0 59 and lower react native sh react native link mapgis mobile react native js in app js import react component from react import platform stylesheet view permissionsandroid from react native import environment mgmapview from mapgis mobile react native export default class app extends component ongetinstance mapview this mapview mapview this openmap openmap async await requestmultiplepermission var environmnetmodule new environment var environmnet await environmnetmodule createobj await environmnet initialize mapgissample await environmnet requestauthorization await this mapview loadfromfile mapgissample map mapshow wuhan wuhan mapx render return view style styles container mgmapview ref mapview ongetinstance this ongetinstance style styles mapview view function checkgranted granteds const values object values granteds let isgranted true for let i 0 i values length 1 i if values i values i 1 isgranted false break if isgranted values 0 permissionsandroid results granted return true return false async function requestmultiplepermission if platform os ios return try const permissions permissionsandroid permissions write external storage permissionsandroid permissions read phone state const granteds await permissionsandroid requestmultiple permissions if checkgranted granteds throw new error catch err throw new error const styles stylesheet create container flex 1 mapview flex 1 alignself stretch | mapgis gis react-native mobile mapgis-mobile-react-native mapgis-mobile | front_end |
TomCodeX | tomcodex information technology services | server |
|
stellargraph | stellargraph machine learning library logo https raw githubusercontent com stellargraph stellargraph develop stellar graph banner png p align center a href https stellargraph readthedocs io alt docs img src https readthedocs org projects stellargraph badge version latest a a href https github com stellargraph stellargraph discussions alt discussions forum img src https img shields io badge help forum discussions blue svg a a href https pypi org project stellargraph alt pypi img src https img shields io pypi v stellargraph svg a a href https github com stellargraph stellargraph blob develop license alt license img src https img shields io github license stellargraph stellargraph svg a p p align center a href https github com stellargraph stellargraph blob develop contributing md alt contributions welcome img src https img shields io badge contributions welcome brightgreen svg a a href https github com stellargraph stellargraph actions query branch 3amaster alt build status master img src https github com stellargraph stellargraph workflows ci badge svg branch master a a href https github com stellargraph stellargraph actions query branch 3adevelop alt build status develop img src https github com stellargraph stellargraph workflows ci badge svg branch develop a a href https codecov io gh stellargraph stellargraph img src https codecov io gh stellargraph stellargraph branch develop graph badge svg a a href https pypi org project stellargraph alt pypi downloads img alt pypi downloads src https pepy tech badge stellargraph a p stellargraph machine learning library stellargraph is a python library for machine learning on graphs and networks https en wikipedia org wiki graph 28discrete mathematics 29 table of contents introduction introduction getting started getting started getting help getting help example gcn example gcn algorithms algorithms installation installation install stellargraph using pypi install stellargraph using pypi install stellargraph in anaconda python install stellargraph in anaconda python install stellargraph from github source install stellargraph from github source citing citing references references introduction the stellargraph library offers state of the art algorithms for graph machine learning https medium com stellargraph knowing your neighbours machine learning on graphs 9b7c3d0d5896 making it easy to discover patterns and answer questions about graph structured data it can solve many machine learning tasks representation learning for nodes and edges to be used for visualisation and various downstream machine learning tasks classification and attribute inference of nodes https medium com stellargraph can graph machine learning identify hate speech in online social networks 58e3b80c9f7e or edges classification of whole graphs link prediction interpretation of node classification https medium com stellargraph https medium com stellargraph saliency maps for graph machine learning 5cca536974da 8 graph structured data represent entities as nodes or vertices and relationships between them as edges or links and can include data associated with either as attributes for example a graph can contain people as nodes and friendships between them as links with data like a person s age and the date a friendship was established stellargraph supports analysis of many kinds of graphs homogeneous with nodes and links of one type heterogeneous with more than one type of nodes and or links knowledge graphs extreme heterogeneous graphs with thousands of types of edges graphs with or without data associated with nodes graphs with edge weights stellargraph is built on tensorflow 2 https tensorflow org and its keras high level api https www tensorflow org guide keras as well as pandas https pandas pydata org and numpy https www numpy org it is thus user friendly modular and extensible it interoperates smoothly with code that builds on these such as the standard keras layers and scikit learn http scikit learn github io stable so it is easy to augment the core graph machine learning algorithms provided by stellargraph it is thus also easy to install with pip or anaconda installation getting started the numerous detailed and narrated examples demos are a good way to get started with stellargraph there is likely to be one that is similar to your data or your problem if not let us know getting help demos https stellargraph readthedocs io en stable demos index html you can start working with the examples immediately in google colab or binder by clicking the https colab research google com assets colab badge svg and https mybinder org badge logo svg badges within each jupyter notebook alternatively you can run download a local copy of the demos and run them using jupyter the demos can be downloaded by cloning the master branch of this repository or by using the curl command below bash curl l https github com stellargraph stellargraph archive master zip tar xz strip 1 stellargraph master demos the dependencies required to run most of our demo notebooks locally can be installed using one of the following using pip pip install stellargraph demos using conda conda install c stellargraph stellargraph see installation installation section for more details and more options getting help if you get stuck or have a problem there are many ways to make progress and get help or support read the documentation https stellargraph readthedocs io consult the examples demos contact us ask questions and discuss problems on the stellargraph discussions forum https github com stellargraph stellargraph discussions file an issue https github com stellargraph stellargraph issues new choose send us an email at stellargraph io gmail com mailto stellargraph io gmail com subject question 20about 20the 20stellargraph 20library example gcn one of the earliest deep machine learning algorithms for graphs is a graph convolution network gcn 6 the following example uses it for node classification predicting the class from which a node comes it shows how easy it is to apply using stellargraph and shows how stellargraph integrates smoothly with pandas and tensorflow and libraries built on them data preparation data for stellargraph can be prepared using common libraries like pandas and scikit learn python import pandas as pd from sklearn import model selection def load my data your own code to load data into pandas dataframes e g from csv files or a database nodes edges targets load my data use scikit learn to compute training and test sets train targets test targets model selection train test split targets train size 0 5 graph machine learning model this is the only part that is specific to stellargraph the machine learning model consists of some graph convolution layers followed by a layer to compute the actual predictions as a tensorflow tensor stellargraph makes it easy to construct all of these layers via the gcn model class it also makes it easy to get input data in the right format via the stellargraph graph data type and a data generator python import stellargraph as sg import tensorflow as tf convert the raw data into stellargraph s graph format for faster operations graph sg stellargraph nodes edges generator sg mapper fullbatchnodegenerator graph method gcn two layers of gcn each with hidden dimension 16 gcn sg layer gcn layer sizes 16 16 generator generator x inp x out gcn in out tensors create the input and output tensorflow tensors use tensorflow keras to add a layer to compute the one hot predictions predictions tf keras layers dense units len ground truth targets columns activation softmax x out use the input and output tensors to create a tensorflow keras model model tf keras model inputs x inp outputs predictions training and evaluation the model is a conventional tensorflow keras model and so tasks such as training and evaluation can use the functions offered by keras stellargraph s data generators make it simple to construct the required keras sequences for input data python prepare the model for training with the adam optimiser and an appropriate loss function model compile adam loss categorical crossentropy metrics accuracy train the model on the train set model fit generator flow train targets index train targets epochs 5 check model generalisation on the test set loss accuracy model evaluate generator flow test targets index test targets print f test set loss loss accuracy accuracy this algorithm is spelled out in more detail in its extended narrated notebook gcn demo we provide many more algorithms each with a detailed example demos gcn demo https stellargraph readthedocs io en stable demos node classification gcn node classification html algorithms the stellargraph library currently includes the following algorithms for graph machine learning algorithm description graphsage 1 supports supervised as well as unsupervised representation learning node classification regression and link prediction for homogeneous networks the current implementation supports multiple aggregation methods including mean maxpool meanpool and attentional aggregators hinsage extension of graphsage algorithm to heterogeneous networks supports representation learning node classification regression and link prediction regression for heterogeneous graphs the current implementation supports mean aggregation of neighbour nodes taking into account their types and the types of links between them attri2vec 4 supports node representation learning node classification and out of sample node link prediction for homogeneous graphs with node attributes graph attention network gat 5 the gat algorithm supports representation learning and node classification for homogeneous graphs there are versions of the graph attention layer that support both sparse and dense adjacency matrices graph convolutional network gcn 6 the gcn algorithm supports representation learning and node classification for homogeneous graphs there are versions of the graph convolutional layer that support both sparse and dense adjacency matrices cluster graph convolutional network cluster gcn 10 an extension of the gcn algorithm supporting representation learning and node classification for homogeneous graphs cluster gcn scales to larger graphs and can be used to train deeper gcn models using stochastic gradient descent simplified graph convolutional network sgc 7 the sgc network algorithm supports representation learning and node classification for homogeneous graphs it is an extension of the gcn algorithm that smooths the graph to bring in more distant neighbours of nodes without using multiple layers approximate personalized propagation of neural predictions ppnp appnp 9 the a ppnp algorithm supports fast and scalable representation learning and node classification for attributed homogeneous graphs in a semi supervised setting first a multilayer neural network is trained using the node attributes as input the predictions from the latter network are then diffused across the graph using a method based on personalized pagerank node2vec 2 the node2vec and deepwalk algorithms perform unsupervised representation learning for homogeneous networks taking into account network structure while ignoring node attributes the node2vec algorithm is implemented by combining stellargraph s random walk generator with the word2vec algorithm from gensim https radimrehurek com gensim learned node representations can be used in downstream machine learning models implemented using scikit learn https scikit learn org stable keras https keras io tensorflow https www tensorflow org or any other python machine learning library metapath2vec 3 the metapath2vec algorithm performs unsupervised metapath guided representation learning for heterogeneous networks taking into account network structure while ignoring node attributes the implementation combines stellargraph s metapath guided random walk generator and gensim https radimrehurek com gensim word2vec algorithm as with node2vec the learned node representations node embeddings can be used in downstream machine learning models to solve tasks such as node classification link prediction etc for heterogeneous networks relational graph convolutional network 11 the rgcn algorithm performs semi supervised learning for node representation and node classification on knowledge graphs rgcn extends gcn to directed graphs with multiple edge types and works with both sparse and dense adjacency matrices complex 12 the complex algorithm computes embeddings for nodes entities and edge types relations in knowledge graphs and can use these for link prediction graphwave 13 graphwave calculates unsupervised structural embeddings via wavelet diffusion through the graph supervised graph classification a model for supervised graph classification based on gcn 6 layers and mean pooling readout watch your step 14 the watch your step algorithm computes node embeddings by using adjacency powers to simulate expected random walks deep graph infomax 15 deep graph infomax trains unsupervised gnns to maximize the shared information between node level and graph level features continuous time dynamic network embeddings ctdne 16 supports time respecting random walks which can be used in a similar way as in node2vec for unsupervised representation learning distmult 17 the distmult algorithm computes embeddings for nodes entities and edge types relations in knowledge graphs and can use these for link prediction dgcnn 18 the deep graph convolutional neural network dgcnn algorithm for supervised graph classification tgcn 19 the gcn lstm model in stellargraph follows the temporal graph convolutional network architecture proposed in the tgcn paper with a few enhancements in the layers architecture installation stellargraph is a python 3 library and we recommend using python version 3 6 the required python version can be downloaded and installed from python org https python org alternatively use the anaconda python environment available from anaconda com https www anaconda com products individual downloads the stellargraph library can be installed from pypi from anaconda cloud or directly from github as described below install stellargraph using pypi to install stellargraph library from pypi https pypi org using pip execute the following command pip install stellargraph some of the examples demos require installing additional dependencies as well as stellargraph to install these dependencies as well as stellargraph using pip execute the following command pip install stellargraph demos the community detection demos require python igraph which is only available on some platforms to install this in addition to the other demo requirements pip install stellargraph demos igraph install stellargraph in anaconda python the stellargraph library is available an anaconda cloud https anaconda org stellargraph stellargraph and can be installed in anaconda python https anaconda com using the command line conda tool execute the following command conda install c stellargraph stellargraph install stellargraph from github source first clone the stellargraph repository using git git clone https github com stellargraph stellargraph git then cd to the stellargraph folder and install the library by executing the following commands cd stellargraph pip install some of the examples in the demos directory require installing additional dependencies as well as stellargraph to install these dependencies as well as stellargraph using pip execute the following command pip install demos citing stellargraph is designed developed and supported by csiro s data61 https data61 csiro au if you use any part of this library in your research please cite it using the following bibtex entry latex misc stellargraph author csiro s data61 title stellargraph machine learning library year 2018 publisher github journal github repository howpublished url https github com stellargraph stellargraph references 1 inductive representation learning on large graphs w l hamilton r ying and j leskovec neural information processing systems nips 2017 link https arxiv org abs 1706 02216 webpage https snap stanford edu graphsage 2 node2vec scalable feature learning for networks a grover j leskovec acm sigkdd international conference on knowledge discovery and data mining kdd 2016 link https snap stanford edu node2vec 3 metapath2vec scalable representation learning for heterogeneous networks yuxiao dong nitesh v chawla and ananthram swami acm sigkdd international conference on knowledge discovery and data mining kdd 135 144 2017 link https ericdongyx github io metapath2vec m2v html 4 attributed network embedding via subspace discovery d zhang y jie x zhu and c zhang data mining and knowledge discovery 2019 link https link springer com article 10 1007 s10618 019 00650 2 5 graph attention networks p veli kovi et al international conference on learning representations iclr 2018 link https arxiv org abs 1710 10903 6 graph convolutional networks gcn semi supervised classification with graph convolutional networks thomas n kipf max welling international conference on learning representations iclr 2017 link https github com tkipf gcn 7 simplifying graph convolutional networks f wu t zhang a h de souza c fifty t yu and k q weinberger international conference on machine learning icml 2019 link https arxiv org abs 1902 07153 8 adversarial examples on graph data deep insights into attack and defense h wu c wang y tyshetskiy a docherty k lu and l zhu ijcai 2019 link https arxiv org abs 1903 01610 9 predict then propagate graph neural networks meet personalized pagerank j klicpera a bojchevski a and s g nnemann iclr 2019 arxiv 1810 05997 link https arxiv org abs 1810 05997 10 cluster gcn an efficient algorithm for training deep and large graph convolutional networks w chiang x liu s si y li s bengio and c hsiej kdd 2019 arxiv 1905 07953 link https arxiv org abs 1905 07953 11 modeling relational data with graph convolutional networks m schlichtkrull t n kipf p bloem r van den berg i titov and m welling european semantic web conference 2018 arxiv 1609 02907 link https arxiv org pdf 1703 06103 pdf 12 complex embeddings for simple link prediction t trouillon j welbl s riedel gaussier and g bouchard icml 2016 link http jmlr org proceedings papers v48 trouillon16 pdf 13 learning structural node embeddings via diffusion wavelets c donnat m zitnik d hallac and j leskovec sigkdd 2018 arxiv 1710 10321 link https arxiv org pdf 1710 10321 pdf 14 watch your step learning node embeddings via graph attention s abu el haija b perozzi r al rfou and a alemi nips 2018 arxiv 1710 09599 link https arxiv org pdf 1710 09599 pdf 15 deep graph infomax p veli kovi w fedus w l hamilton p lio y bengio r d hjelm international conference on learning representations iclr 2019 arxiv 1809 10341 link https arxiv org pdf 1809 10341 pdf 16 continuous time dynamic network embeddings giang hoang nguyen john boaz lee ryan a rossi nesreen k ahmed eunyee koh and sungchul kim proceedings of the 3rd international workshop on learning representations for big networks www bignet 2018 link https dl acm org doi 10 1145 3184558 3191526 17 embedding entities and relations for learning and inference in knowledge bases bishan yang wen tau yih xiaodong he jianfeng gao and li deng iclr 2015 arxiv 1412 6575 link https arxiv org pdf 1412 6575 pdf 18 an end to end deep learning architecture for graph classification muhan zhang zhicheng cui marion neumann and yixin chen aaai 2018 link https www cse wustl edu yixin chen public dgcnn pdf 19 t gcn a temporal graph convolutional network for traffic prediction ling zhao yujiao song chao zhang yu liu pu wang tao lin min deng and haifeng li ieee transactions on intelligent transportation systems 2019 link https ieeexplore ieee org document 8809901 | graphs machine-learning machine-learning-algorithms graph-convolutional-networks networkx geometric-deep-learning saliency-map interpretability heterogeneous-networks graph-neural-networks graph-analysis graph-machine-learning gcn link-prediction stellargraph-library graph-data python deep-learning data-science | ai |
Advanced-Computer-Vision | advanced computer vision lecturer prof chiou shann fuh https www csie ntu edu tw fuh br course website http cv2 csie ntu edu tw cv cv2 htm | block-matching-algorithm computer-vision | ai |
design-system | appsmith design systems this repository contains all the design system that appsmith maintains contents please see the readme s of the individual repositories to understand how to use them design system old warning this package is deprecated starting march 1 2023 package appsmithorg design system old https www npmjs com package appsmithorg design system old readme https github com appsmithorg design system blob release packages design system old readme md storybook https design system appsmith com old design system package appsmithorg design system https www npmjs com package appsmithorg design system readme https github com appsmithorg design system blob release packages design system readme md storybook https design system appsmith com | components design-system ui-components react-components react reactjs ui-library | os |
FYP | final year project b eng in mechatronic engineering this android app was built for the final year project of my b eng in dublin city university ireland it was an exploration into the capabilities for ml based image classification to innovate within the calorie counting diet management applicaton industry namely the application uses a retrained version of the mobilenets image classification model to perform this on android implemented with the lightweight tensorflow lite ml library this was on the leading edge of mobile based ml in 2017 18 please excuse the code quality my project was based on the apps functionality and on my research so code quality lapsed in the rush to complete the project it will be cleaned up eventually copyright 2019 lukescales | android-application machine-learning healthcare-application | server |
data-scraping-sofascore | readme sofascore scraper overview this data engineering project performs some detailed data mining operations reaching the website sofascore https www sofascore com and scraping data about football players and managers from the main european leagues then it makes sure all the data is safely stored in a relational database ready to be exploited by the user the data for the selected football leagues all the team names are collected for every team each player is scraped and a series of information is stored in a database 1 name 2 nationality 3 date of birth 4 height 5 preferred foot 6 position on the pitch 7 shirt number information about managers is parsed as well 1 name 2 date of birth 3 nationality 4 preferred formation 5 average points per game 6 games won 7 games drawn 8 games lost moreover extra data about the various teams is obtained from an external api https thesportsdb com api php and stored in the db 1 name 2 short name 3 alternative name 4 foundation year 5 stadium name 6 stadium picture url 7 stadium description 8 stadium location 9 stadium capacity 10 team website 11 team facebook 12 team twitter 13 team instagram 14 team description if the data related to a certain league hasn t been scraped before it will be simply added to the database if otherwise the data from the selected league is already present in the database this data will be overwritten by the current one usage as a first step it s important to write the correct username and password in config py then just run the following commands pip install r requirements txt python main py s p l b cli arg action s scrapes teams and players from serie a p scrapes teams and players from premier league l scrapes teams and players from la liga b scrapes teams and players from bundesliga the user can choose which league or combination of leagues to scrape and to create update the database with created by daniel saban sagi elfassi | dataengineering datamining webscraping relational-databases parser etl-pipeline rest-api | server |
Awesome-LLM-RAG | awesome llm rag paper enhancing large language models with retrieval augmented generation assets rag png paper understanding retrieval augmentation for long form question answering 2023 10 18 arxiv https arxiv org abs 2310 12150 self rag learning to retrieve generate and critique through self reflection 2023 10 17 arxiv https arxiv org abs 2310 11511 code https github com akariasai self rag regavae a retrieval augmented gaussian mixture variational auto encoder for language modeling 2023 10 16 arxiv https arxiv org abs 2310 10567 chameleon a heterogeneous and disaggregated accelerator system for retrieval augmented language models 2023 10 15 arxiv https arxiv org abs 2310 09949 instructretro instruction tuning post retrieval augmented pretraining 2023 10 11 arxiv https arxiv org abs 2310 07713 goodtriever adaptive toxicity mitigation with retrieval augmented models 2023 10 11 arxiv https arxiv org abs 2310 07589 retrieve anything to augment large language models 2023 10 11 arxiv https arxiv org abs 2310 07554 verifai verified generative ai 2023 10 11 arxiv https arxiv org abs 2307 02796 crossing the threshold idiomatic machine translation through retrieval augmentation and loss weighting 2023 10 10 arxiv https arxiv org abs 2310 07081 raucg retrieval augmented unsupervised counter narrative generation for hate speech 2023 10 09 arxiv https arxiv org abs 2310 05650 grove a retrieval augmented complex story generation framework with a forest of evidence 2023 10 08 arxiv https arxiv org abs 2310 05388 augmented embeddings for custom retrievals 2023 10 08 arxiv https arxiv org abs 2310 05380 retrieval generation synergy augmented large language models 2023 10 08 arxiv https arxiv org abs 2310 05149 self knowledge guided retrieval augmentation for large language models 2023 10 08 arxiv https arxiv org abs 2310 05002 recomp improving retrieval augmented lms with compression and selective augmentation 2023 10 06 arxiv https arxiv org abs 2310 04408 keyword augmented retrieval novel framework for information retrieval integrated with speech interface 2023 10 06 arxiv https arxiv org abs 2310 04205 enhancing financial sentiment analysis via retrieval augmented large language models 2023 10 06 arxiv https arxiv org abs 2310 04027 retrieval augmented generation to improve math question answering trade offs between groundedness and human preference 2023 10 04 arxiv https arxiv org abs 2310 03184 making retrieval augmented language models robust to irrelevant context 2023 10 02 arxiv https arxiv org abs 2310 01558 ra dit retrieval augmented dual instruction tuning 2023 10 08 arxiv https arxiv org abs 2310 01352 btr binary token representations for efficient retrieval augmented language models 2023 10 02 arxiv https arxiv org abs 2310 01329 fine grained late interaction multi modal retrieval for retrieval augmented visual question answering 2023 09 29 arxiv https arxiv org abs 2309 17133 interpretable long form legal question answering with retrieval augmented large language models 2023 09 29 arxiv https arxiv org abs 2309 17050 ragas automated evaluation of retrieval augmented generation 2023 09 26 arxiv https arxiv org abs 2309 15217 furthest reasoning with plan assessment stable reasoning path with retrieval augmented large language models 2023 09 22 arxiv https arxiv org abs 2309 12767 ruel retrieval augmented user representation with edge browser logs for sequential recommendation 2023 09 19 arxiv https arxiv org abs 2309 10469 revisiting and improving retrieval augmented deep assertion generation 2023 09 18 arxiv https arxiv org abs 2309 10264 recap retrieval augmented audio captioning 2023 09 18 arxiv https arxiv org abs 2309 09836 retrieval augmented text to audio generation 2023 09 14 arxiv https arxiv org abs 2309 08051 rap gen retrieval augmented patch generation with codet5 for automatic program repair 2023 09 12 arxiv https arxiv org abs 2309 06057 retrieval augmented meta learning for low resource text classification 2023 09 10 arxiv https arxiv org abs 2309 04979 benchmarking large language models in retrieval augmented generation 2023 09 04 arxiv https arxiv org abs 2309 01431 ramp retrieval augmented mos prediction via confidence based dynamic weighting 2023 08 31 arxiv https arxiv org abs 2308 16488 ralle a framework for developing and evaluating retrieval augmented large language models 2023 10 16 arxiv https arxiv org abs 2308 10633 differentiable retrieval augmentation via generative language modeling for e commerce query intent classification 2023 09 15 arxiv https arxiv org abs 2308 09308 rspell retrieval augmented framework for domain adaptive chinese spelling check 2023 08 16 arxiv https arxiv org abs 2308 08176 enhancing performance on seen and unseen dialogue scenarios using retrieval augmented end to end task oriented system 2023 08 16 arxiv https arxiv org abs 2308 08169 raven in context learning with retrieval augmented encoder decoder language models 2023 08 15 arxiv https arxiv org abs 2308 07922 diffusion based augmentation for captioning and retrieval in cultural heritage 2023 08 14 arxiv https arxiv org abs 2308 07151 encode store retrieve enhancing memory augmentation through language encoded egocentric perception 2023 08 10 arxiv https arxiv org abs 2308 05822 hybrid retrieval augmented generation for real time composition assistance 2023 08 08 arxiv https arxiv org abs 2308 04215 rahnet retrieval augmented hybrid network for long tailed graph classification 2023 09 07 arxiv https arxiv org abs 2308 02335 retrieval augmented generation and representative vector summarization for large unstructured textual data in medical education 2023 08 01 arxiv https arxiv org abs 2308 00479 select and augment enhanced dense retrieval knowledge graph augmentation 2023 07 28 arxiv https arxiv org abs 2307 15776 exploring annotation free image captioning with retrieval augmented pseudo sentence generation 2023 07 28 arxiv https arxiv org abs 2307 14750 tabr unlocking the power of retrieval augmented tabular deep learning 2023 07 26 arxiv https arxiv org abs 2307 14338 rraml reinforced retrieval augmented machine learning 2023 07 27 arxiv https arxiv org abs 2307 12798 investigating the factual knowledge boundary of large language models with retrieval augmentation 2023 07 23 arxiv https arxiv org abs 2307 11019 soft prompt tuning for augmenting dense retrieval with large language models 2023 08 29 arxiv https arxiv org abs 2307 08303 animate a story storytelling with retrieval augmented video generation 2023 07 13 arxiv https arxiv org abs 2307 06940 prompt generate train pgt few shot domain adaption of retrieval augmented generation models for open book question answering 2023 07 25 arxiv https arxiv org abs 2307 05915 retrieval augmented gpt 3 5 based text to sql framework with sample aware prompting and dynamic revision chain 2023 09 04 arxiv https arxiv org abs 2307 05074 trac trustworthy retrieval augmented chatbot 2023 07 06 arxiv https arxiv org abs 2307 04642 improving retrieval augmented large language models via data importance learning 2023 07 06 arxiv https arxiv org abs 2307 03027 diverse retrieval augmented in context learning for dialogue state tracking 2023 07 03 arxiv https arxiv org abs 2307 01453 when not to trust language models investigating effectiveness of parametric and non parametric memories 2023 07 02 arxiv https arxiv org abs 2212 10511 leandojo theorem proving with retrieval augmented language models 2023 06 27 arxiv https arxiv org abs 2306 15626 sail search augmented instruction learning 2023 06 25 arxiv https arxiv org abs 2305 15225 retrieval based transformer for table augmentation 2023 06 20 arxiv https arxiv org abs 2306 11843 speech to text adapter and speech to entity retriever augmented llms for speech understanding 2023 06 08 arxiv https arxiv org abs 2306 07944 weakly supervised scientific document classification via retrieval augmented multi stage training 2023 06 12 arxiv https arxiv org abs 2306 07193 reta llm a retrieval augmented large language model toolkit 2023 06 08 arxiv https arxiv org abs 2306 05212 large language models can be easily distracted by irrelevant context 2023 06 06 arxiv https arxiv org abs 2302 00093 reimagining retrieval augmented language models for answering queries 2023 06 01 arxiv https arxiv org abs 2306 01061 lmcap few shot multilingual image captioning by retrieval augmented language model prompting 2023 05 31 arxiv https arxiv org abs 2305 19821 label retrieval augmented diffusion models for learning from noisy labels 2023 05 30 arxiv https arxiv org abs 2305 19518 prompt guided retrieval augmentation for non knowledge intensive tasks 2023 05 28 arxiv https arxiv org abs 2305 17653 augmentation adapted retriever improves generalization of language models as generic plug in 2023 05 26 arxiv https arxiv org abs 2305 17331 improving accuracy of gpt 3 4 results on biomedical data using a retrieval augmented language model 2023 05 30 arxiv https arxiv org abs 2305 17116 surface based retrieval reduces perplexity of retrieval augmented language models 2023 07 04 arxiv https arxiv org abs 2305 16243 enhancing retrieval augmented large language models with iterative retrieval generation synergy 2023 05 24 arxiv https arxiv org abs 2305 15294 referral augmentation for zero shot information retrieval 2023 05 24 arxiv https arxiv org abs 2305 15098 enabling large language models to generate text with citations 2023 05 24 arxiv https arxiv org abs 2305 14627 query rewriting for retrieval augmented large language models 2023 05 23 arxiv https arxiv org abs 2305 14283 retrieval augmented multi label text classification 2023 05 22 arxiv https arxiv org abs 2305 13058 malm mask augmentation based local matching for food recipe retrieval 2023 05 18 arxiv https arxiv org abs 2305 11327 tram a token level retrieval augmented mechanism for source code summarization 2023 05 18 arxiv https arxiv org abs 2305 11074 active retrieval augmented generation 2023 05 11 arxiv https arxiv org abs 2305 06983 augmenting passage representations with query generation for enhanced cross lingual dense retrieval 2023 05 06 arxiv https arxiv org abs 2305 03950 damo nlp at semeval 2023 task 2 a unified retrieval augmented system for multilingual named entity recognition 2023 05 16 arxiv https arxiv org abs 2305 03688 retrieval augmented chest x ray report generation using openai gpt models 2023 05 05 arxiv https arxiv org abs 2305 03660 lift yourself up retrieval augmented text generation with self memory 2023 05 17 arxiv https arxiv org abs 2305 02437 discern and answer mitigating the impact of misinformation in retrieval augmented models with discriminators 2023 05 02 arxiv https arxiv org abs 2305 01579 retrieval based knowledge augmented vision language pre training 2023 08 06 arxiv https arxiv org abs 2304 13923 a data augmentation perspective on diffusion models and retrieval 2023 04 20 arxiv https arxiv org abs 2304 10253 lader log augmented dense retrieval for biomedical literature search 2023 04 10 arxiv https arxiv org abs 2304 04590 remodiffuse retrieval augmented motion diffusion model 2023 04 03 arxiv https arxiv org abs 2304 01116 retrieval augmented classification with decoupled representation 2023 04 11 arxiv https arxiv org abs 2303 13065 retrieving multimodal information for augmented generation a survey 2023 10 07 arxiv https arxiv org abs 2303 10868 on the calibration and uncertainty with p lya gamma augmentation for dialog retrieval models 2023 03 15 arxiv https arxiv org abs 2303 08606 semantic preserving augmentation for robust image text retrieval 2023 03 09 arxiv https arxiv org abs 2303 05692 almanac retrieval augmented language models for clinical medicine 2023 05 31 arxiv https arxiv org abs 2303 01229 ramm retrieval augmented biomedical visual question answering with multi modal pre training 2023 03 01 arxiv https arxiv org abs 2303 00534 retrieved sequence augmentation for protein representation learning 2023 02 24 arxiv https arxiv org abs 2302 12563 x tra improving chest x ray tasks with cross modal retrieval augmentation 2023 02 22 arxiv https arxiv org abs 2302 11352 retrieval augmented image captioning 2023 02 16 arxiv https arxiv org abs 2302 08268 how to train your dragon diverse augmentation towards generalizable dense retrieval 2023 02 14 arxiv https arxiv org abs 2302 07452 vitr augmenting vision transformers with relation focused learning for cross modal information retrieval 2023 07 27 arxiv https arxiv org abs 2302 06350 characterizing attribution and fluency tradeoffs for retrieval augmented large language models 2023 02 14 arxiv https arxiv org abs 2302 05578 re vilm retrieval augmented visual language model for zero and few shot image captioning 2023 02 09 arxiv https arxiv org abs 2302 04858 augmenting zero shot dense retrievers with plug in mixture of memories 2023 02 07 arxiv https arxiv org abs 2302 03754 in context retrieval augmented language models 2023 08 01 arxiv https arxiv org abs 2302 00083 replug retrieval augmented black box language models 2023 05 24 arxiv https arxiv org abs 2301 12652 pre computed memory or on the fly encoding a hybrid approach to retrieval augmentation makes the most of your compute 2023 06 02 arxiv https arxiv org abs 2301 10448 learning customized visual models with retrieval augmented knowledge 2023 01 17 arxiv https arxiv org abs 2301 07094 generation augmented query expansion for code retrieval 2022 12 20 arxiv https arxiv org abs 2212 10692 cross lingual retrieval augmented prompt for low resource languages 2023 07 10 arxiv https arxiv org abs 2212 09651 can retriever augmented language models reason the blame game between the retriever and the language model 2023 05 06 arxiv https arxiv org abs 2212 09146 augtriever unsupervised dense retrieval by scalable data augmentation 2023 03 07 arxiv https arxiv org abs 2212 08841 reveal retrieval augmented visual language pre training with multi source multimodal knowledge memory 2023 04 03 arxiv https arxiv org abs 2212 05221 retrieval augmented multimodal language modeling 2023 06 05 arxiv https arxiv org abs 2211 12561 retrieval augmented generative question answering for event argument extraction 2022 11 13 arxiv https arxiv org abs 2211 07067 suffix retrieval augmented language modeling 2023 03 14 arxiv https arxiv org abs 2211 03053 quill query intent with large language models using retrieval augmentation and multi stage distillation 2022 10 27 arxiv https arxiv org abs 2210 15718 xricl cross lingual retrieval augmented in context learning for cross lingual text to sql semantic parsing 2022 10 24 arxiv https arxiv org abs 2210 13693 retrieval augmentation for commonsense reasoning a unified approach 2022 10 23 arxiv https arxiv org abs 2210 12887 retrieval augmentation for t5 re ranker using external sources 2022 10 11 arxiv https arxiv org abs 2210 05145 improving robustness of retrieval augmented translation via shuffling of suggestions 2022 10 10 arxiv https arxiv org abs 2210 05059 improving retrieval augmented neural machine translation by controlling source and fuzzy match interactions 2022 10 10 arxiv https arxiv org abs 2210 05047 retrieval augmented visual question answering with outside knowledge 2022 10 29 arxiv https arxiv org abs 2210 03809 murag multimodal retrieval augmented generator for open question answering over images and text 2022 10 20 arxiv https arxiv org abs 2210 02928 improving the domain adaptation of retrieval augmented generation rag models for open domain question answering 2022 10 05 arxiv https arxiv org abs 2210 02627 smallcap lightweight image captioning prompted with retrieval augmentation 2023 03 28 arxiv https arxiv org abs 2209 15323 re imagen retrieval augmented text to image generator 2022 11 21 arxiv https arxiv org abs 2209 14491 fid light efficient and effective retrieval augmented text generation 2022 09 28 arxiv https arxiv org abs 2209 14290 segment augmentation and differentiable ranking for logo retrieval 2022 09 13 arxiv https arxiv org abs 2209 02482 scl rai span based contrastive learning with retrieval augmented inference for unlabeled entity problem in ner 2022 09 24 arxiv https arxiv org abs 2209 01646 improving natural language based audio retrieval with transfer learning and audio text augmentations 2022 10 29 arxiv https arxiv org abs 2208 11460 category level pose retrieval with contrastive features learnt with occlusion augmentation 2022 10 12 arxiv https arxiv org abs 2208 06195 atlas few shot learning with retrieval augmented language models 2022 11 16 arxiv https arxiv org abs 2208 03299 a feature space multimodal data augmentation technique for text video retrieval 2022 08 03 arxiv https arxiv org abs 2208 02080 paired cross modal data augmentation for fine grained image to text retrieval 2022 07 28 arxiv https arxiv org abs 2207 14428 retrieval augmented transformer for image captioning 2022 08 22 arxiv https arxiv org abs 2207 13162 text guided synthesis of artistic images with retrieval augmented diffusion models 2022 07 26 arxiv https arxiv org abs 2207 13038 mqretnn multi horizon time series forecasting with retrieval augmentation 2022 09 08 arxiv https arxiv org abs 2207 10517 multi task retrieval augmented text generation with relevance sampling 2022 07 06 arxiv https arxiv org abs 2207 03030 bashexplainer retrieval augmented bash code comment generation based on fine tuned codebert 2022 06 27 arxiv https arxiv org abs 2206 13325 improving contrastive learning of sentence embeddings with case augmented positives and retrieved negatives 2022 06 06 arxiv https arxiv org abs 2206 02457 augmenting scientific creativity with retrieval across knowledge domains 2022 12 14 arxiv https arxiv org abs 2206 01328 zusammenqa data augmentation with specialized models for cross lingual open retrieval question answering system 2022 05 30 arxiv https arxiv org abs 2205 14981 cache augmented inbatch importance resampling for training recommender retriever 2022 05 30 arxiv https arxiv org abs 2205 14859 decoupling knowledge from memorization retrieval augmented prompt learning 2023 09 19 arxiv https arxiv org abs 2205 14704 retrieval augmented multilingual keyphrase generation with retriever generator iterative training 2022 06 01 arxiv https arxiv org abs 2205 10471 convex augmentation for total variation based phase retrieval 2022 04 21 arxiv https arxiv org abs 2205 00834 retrieval enhanced data augmentation for question answering on privacy policies 2023 04 22 arxiv https arxiv org abs 2204 08952 unsupervised cross task generalization via retrieval augmentation 2022 10 17 arxiv https arxiv org abs 2204 07937 end to end table question answering via retrieval augmented generation 2022 03 30 arxiv https arxiv org abs 2203 16714 augmenting document representations for dense retrieval with interpolation and perturbation 2022 03 16 arxiv https arxiv org abs 2203 07735 reacc a retrieval augmented code completion framework 2022 03 15 arxiv https arxiv org abs 2203 07722 race retrieval augmented commit message generation 2022 10 22 arxiv https arxiv org abs 2203 02700 retrieval augmented classification for long tail visual recognition 2022 02 22 arxiv https arxiv org abs 2202 11233 retrieval augmented reinforcement learning 2022 05 24 arxiv https arxiv org abs 2202 08417 inpars data augmentation for information retrieval using large language models 2022 02 10 arxiv https arxiv org abs 2202 05144 a survey on retrieval augmented text generation 2022 02 13 arxiv https arxiv org abs 2202 01110 novelty controlled paraphrase generation with retrieval augmented conditional prompt tuning 2022 03 12 arxiv https arxiv org abs 2202 00535 neuro symbolic language modeling with automaton augmented retrieval 2022 06 09 arxiv https arxiv org abs 2201 12431 noise augmented privacy preserving empirical risk minimization with dual purpose regularizer and privacy budget retrieval and recycling 2021 10 16 arxiv https arxiv org abs 2110 08676 controllable semantic parsing via retrieval augmentation 2022 02 23 arxiv https arxiv org abs 2110 08458 retronlu retrieval augmented task oriented semantic parsing 2021 09 21 arxiv https arxiv org abs 2109 10410 robust retrieval augmented generation for zero shot slot filling 2021 09 13 arxiv https arxiv org abs 2108 13934 retrieval augmented code generation and summarization 2021 09 10 arxiv https arxiv org abs 2108 11601 two pronged strategy lightweight augmented graph network hashing for scalable image retrieval 2021 08 09 arxiv https arxiv org abs 2108 03914 retrieval augmented transformer xl for close domain dialog generation 2021 05 19 arxiv https arxiv org abs 2105 09235 cross modal retrieval augmentation for multi modal classification 2021 04 16 arxiv https arxiv org abs 2104 08108 retrieval augmentation reduces hallucination in conversation 2021 04 15 arxiv https arxiv org abs 2104 07567 retrieval augmentation for deep neural networks 2021 04 26 arxiv https arxiv org abs 2102 13030 efficient retrieval augmented generation from unstructured knowledge for task oriented dialog 2021 02 08 arxiv https arxiv org abs 2102 04643 memory augmented sequential paragraph retrieval for multi hop question answering 2021 02 07 arxiv https arxiv org abs 2102 03741 augmenting machine learning with information retrieval to recommend real cloned code methods for code completion 2020 10 02 arxiv https arxiv org abs 2010 00964 neural retrieval for question answering with cross attention supervised data augmentation 2020 09 29 arxiv https arxiv org abs 2009 13815 generation augmented retrieval for open domain question answering 2021 08 06 arxiv https arxiv org abs 2009 08553 retrieve synonymous keywords for frequent queries in sponsored search in a data augmentation way 2020 08 05 arxiv https arxiv org abs 2008 01969 tree augmented cross modal encoding for complex query video retrieval 2020 07 05 arxiv https arxiv org abs 2007 02503 on the fly information retrieval augmentation for language models 2020 07 03 arxiv https arxiv org abs 2007 01528 retrieval augmented generation for code summarization via hybrid gnn 2021 05 12 arxiv https arxiv org abs 2006 05405 retrieval augmented generation for knowledge intensive nlp tasks 2021 04 12 arxiv https arxiv org abs 2005 11401 exemplar vae linking generative models nearest neighbor retrieval and data augmentation 2020 11 24 arxiv https arxiv org abs 2004 04795 realm retrieval augmented language model pre training 2020 02 10 arxiv https arxiv org abs 2002 08909 learning test time augmentation for content based image retrieval 2022 07 05 arxiv https arxiv org abs 2002 01642 multi modal music information retrieval augmenting audio analysis with visual computing for improved music video analysis 2020 02 01 arxiv https arxiv org abs 2002 00251 web table extraction retrieval and augmentation a survey 2020 02 05 arxiv https arxiv org abs 2002 00207 graphene a precise biomedical literature retrieval engine with graph augmented deep learning and external knowledge empowerment 2019 11 20 arxiv https arxiv org abs 1911 00760 neural argument generation augmented with externally retrieved evidence 2018 05 25 arxiv https arxiv org abs 1805 10254 gradient augmented information retrieval with autoencoders and semantic hashing 2018 03 12 arxiv https arxiv org abs 1803 04494 retrieval augmented convolutional neural networks for improved robustness against adversarial examples 2018 02 26 arxiv https arxiv org abs 1802 09502 discriminative learning of open vocabulary object retrieval and localization by negative phrase augmentation 2018 09 04 arxiv https arxiv org abs 1711 09509 paper automatic hallucination assessment for aligned large language models via transferable adversarial attacks 2023 10 19 arxiv https arxiv org abs 2310 12516 self rag learning to retrieve generate and critique through self reflection 2023 10 17 arxiv https arxiv org abs 2310 11511 towards reducing hallucination in extracting information from financial reports using large language models 2023 10 16 arxiv https arxiv org abs 2310 10760 in context pretraining language modeling beyond document boundaries 2023 10 18 arxiv https arxiv org abs 2310 10638 mechgpt a language based strategy for mechanics and materials modeling that connects knowledge across scales disciplines and modalities 2023 10 16 arxiv https arxiv org abs 2310 10445 carexpert leveraging large language models for in car conversational question answering 2023 10 14 arxiv https arxiv org abs 2310 09536 towards example based nmt with multi levenshtein transformers 2023 10 13 arxiv https arxiv org abs 2310 08967 gentkg generative forecasting on temporal knowledge graph 2023 10 11 arxiv https arxiv org abs 2310 07793 survey on factuality in large language models knowledge retrieval and domain specificity 2023 10 18 arxiv https arxiv org abs 2310 07521 the solution for the cvpr2023 nice image captioning challenge 2023 10 10 arxiv https arxiv org abs 2310 06879 gpt 4 as an agronomist assistant answering agriculture exams using large language models 2023 10 12 arxiv https arxiv org abs 2310 06225 glitter or gold deriving structured insights from sustainability reports via large language models 2023 10 09 arxiv https arxiv org abs 2310 05628 llm4vv developing llm driven testsuite for compiler validation 2023 10 07 arxiv https arxiv org abs 2310 04963 retrieval meets long context large language models 2023 10 04 arxiv https arxiv org abs 2310 03025 chatmap large language model interaction with cartographic data 2023 09 28 arxiv https arxiv org abs 2310 01429 attention sorting combats recency bias in long context language models 2023 09 28 arxiv https arxiv org abs 2310 01427 pdftriage question answering over long structured documents 2023 09 16 arxiv https arxiv org abs 2309 08872 pace lm prompting and augmentation for calibrated confidence estimation with gpt 4 in cloud incident root cause analysis 2023 09 29 arxiv https arxiv org abs 2309 05833 kani a lightweight and highly hackable framework for building language model applications 2023 09 11 arxiv https arxiv org abs 2309 05542 scaling autoregressive multi modal models pretraining and instruction tuning 2023 09 05 arxiv https arxiv org abs 2309 02591 a study on the implementation of generative ai services using an enterprise data based llm application architecture 2023 09 18 arxiv https arxiv org abs 2309 01105 memory vq compression for tractable internet scale memory 2023 08 28 arxiv https arxiv org abs 2308 14903 american stories a large scale structured text dataset of historical u s newspapers 2023 08 23 arxiv https arxiv org abs 2308 12477 domain adaptive code completion via language models and decoupled domain databases 2023 09 20 arxiv https arxiv org abs 2308 09313 answering unseen questions with smaller language models using rationale generation and dense retrieval 2023 10 12 arxiv https arxiv org abs 2308 04711 teaching smaller language models to generalise to unseen compositional questions 2023 08 20 arxiv https arxiv org abs 2308 00946 evaluating correctness and faithfulness of instruction following models for question answering 2023 07 31 arxiv https arxiv org abs 2307 16877 alleviating the long tail problem in conversational recommender systems 2023 07 21 arxiv https arxiv org abs 2307 11650 meta training with demonstration retrieval for efficient few shot learning 2023 06 30 arxiv https arxiv org abs 2307 00119 rapgen an approach for fixing code inefficiencies in zero shot 2023 06 29 arxiv https arxiv org abs 2306 17077 long range language modeling with self retrieval 2023 06 23 arxiv https arxiv org abs 2306 13421 encyclopedic vqa visual questions about detailed properties of fine grained categories 2023 07 24 arxiv https arxiv org abs 2306 09224 poet a generative model of protein families as sequences of sequences 2023 06 09 arxiv https arxiv org abs 2306 06156 timelineqa a benchmark for question answering over timelines 2023 06 01 arxiv https arxiv org abs 2306 01069 knowledge graph augmented language models for knowledge grounded dialogue generation 2023 05 30 arxiv https arxiv org abs 2305 18846 multimodal relation extraction with cross modal retrieval and synthesis 2023 05 25 arxiv https arxiv org abs 2305 16166 learning answer generation using supervision from automatic question answering evaluators 2023 05 24 arxiv https arxiv org abs 2305 15344 adapting language models to compress contexts 2023 05 24 arxiv https arxiv org abs 2305 14788 knn lm does not improve open ended text generation 2023 05 23 arxiv https arxiv org abs 2305 14625 factscore fine grained atomic evaluation of factual precision in long form text generation 2023 10 11 arxiv https arxiv org abs 2305 14251 adaptive chameleon or stubborn sloth revealing the behavior of large language models in knowledge conflicts 2023 10 02 arxiv https arxiv org abs 2305 13300 knowledge retrieval task oriented dialog systems with semi supervision 2023 05 22 arxiv https arxiv org abs 2305 13199 the web can be your oyster for improving large language models 2023 05 24 arxiv https arxiv org abs 2305 10998 rl4f generating natural language feedback with reinforcement learning for repairing model outputs 2023 07 11 arxiv https arxiv org abs 2305 08844 huatuo 26m a large scale chinese medical qa dataset 2023 05 02 arxiv https arxiv org abs 2305 01526 lamp when large language models meet personalization 2023 05 19 arxiv https arxiv org abs 2304 11406 genegpt augmenting large language models with domain tools for improved access to biomedical information 2023 05 16 arxiv https arxiv org abs 2304 09667 brent bidirectional retrieval enhanced norwegian transformer 2023 04 19 arxiv https arxiv org abs 2304 09649 shall we pretrain autoregressive language models with retrieval a comprehensive study 2023 10 19 arxiv https arxiv org abs 2304 06762 improving image recognition by retrieving from web scale image text data 2023 04 11 arxiv https arxiv org abs 2304 05173 repocoder repository level code completion through iterative retrieval and generation 2023 04 03 arxiv https arxiv org abs 2303 12570 on the generalization ability of retrieval enhanced transformers 2023 02 23 arxiv https arxiv org abs 2302 12128 k nn adapter efficient domain adaptation for black box language models 2023 02 21 arxiv https arxiv org abs 2302 10879 why do nearest neighbor language models work 2023 01 17 arxiv https arxiv org abs 2301 02828 you truly understand what i need intellectual and friendly dialogue agents grounding knowledge and persona 2023 01 06 arxiv https arxiv org abs 2301 02401 demonstrate search predict composing retrieval and language models for knowledge intensive nlp 2023 01 23 arxiv https arxiv org abs 2212 14024 parallel context windows for large language models 2023 08 01 arxiv https arxiv org abs 2212 10947 when not to trust language models investigating effectiveness of parametric and non parametric memories 2023 07 02 arxiv https arxiv org abs 2212 10511 empowering sentence encoders with prompting and label retrieval for zero shot text classification 2023 05 19 arxiv https arxiv org abs 2212 10391 fido fusion in decoder optimized for stronger performance and faster inference 2023 06 02 arxiv https arxiv org abs 2212 08153 neural machine translation with contrastive translation memories 2022 12 06 arxiv https arxiv org abs 2212 03140 clueweb22 10 billion web documents with visual and semantic information 2022 12 01 arxiv https arxiv org abs 2211 15848 large language models struggle to learn long tail knowledge 2023 07 27 arxiv https arxiv org abs 2211 08411 cells a parallel corpus for biomedical lay language generation 2022 11 07 arxiv https arxiv org abs 2211 03818 an efficient memory augmented transformer for knowledge intensive nlp tasks 2022 10 30 arxiv https arxiv org abs 2210 16773 schema aware reference as prompt improves data efficient knowledge graph construction 2023 09 18 arxiv https arxiv org abs 2210 10709 cofar commonsense and factual reasoning in image search 2022 10 16 arxiv https arxiv org abs 2210 08554 variational open domain question answering 2023 05 31 arxiv https arxiv org abs 2210 06345 decoupled context processing for context augmented language modeling 2022 10 11 arxiv https arxiv org abs 2210 05758 core a retrieve then edit framework for counterfactual data generation 2022 11 01 arxiv https arxiv org abs 2210 04873 recitation augmented language models 2023 02 16 arxiv https arxiv org abs 2210 01296 zemi learning zero shot semi parametric language models from multiple tasks 2023 05 22 arxiv https arxiv org abs 2210 00185 multimedia generative script learning for task planning 2023 07 10 arxiv https arxiv org abs 2208 12306 can large language models reason about medical questions 2023 01 24 arxiv https arxiv org abs 2207 08143 memory based model editing at scale 2022 06 13 arxiv https arxiv org abs 2206 06520 knn prompt nearest neighbor zero shot inference 2022 11 01 arxiv https arxiv org abs 2205 13792 long term control for dialogue generation methods and evaluation 2022 05 15 arxiv https arxiv org abs 2205 07352 efficient machine translation domain adaptation 2022 04 26 arxiv https arxiv org abs 2204 12608 a corpus for understanding and generating moral stories 2022 04 20 arxiv https arxiv org abs 2204 09438 augmenting pre trained language models with qa memory for open domain question answering 2023 01 23 arxiv https arxiv org abs 2204 04581 kgi an integrated framework for knowledge intensive language tasks 2022 09 21 arxiv https arxiv org abs 2204 03985 k nn ner named entity recognition with nearest neighbor search 2022 03 31 arxiv https arxiv org abs 2203 17103 evidentiality guided generation for knowledge intensive nlp tasks 2022 05 14 arxiv https arxiv org abs 2112 08688 reason first then respond modular generation for knowledge infused dialogue 2021 11 09 arxiv https arxiv org abs 2111 05204 end to end learning of flowchart grounded task oriented dialogs 2021 12 07 arxiv https arxiv org abs 2109 07263 memory and knowledge augmented language models for inferring salience in long form stories 2021 09 14 arxiv https arxiv org abs 2109 03754 beyond goldfish memory long term open domain conversation 2021 07 15 arxiv https arxiv org abs 2107 07567 fine tune the entire rag architecture including dpr retriever for question answering 2021 06 21 arxiv https arxiv org abs 2106 11517 end to end training of multi document reader and retriever for open domain question answering 2021 12 04 arxiv https arxiv org abs 2106 05346 zero shot slot filling with dpr and rag 2021 04 17 arxiv https arxiv org abs 2104 08610 lingke a fine grained multi turn chatbot for customer service 2018 08 10 arxiv https arxiv org abs 1808 03430 retrieval augmented convolutional neural networks for improved robustness against adversarial examples 2018 02 26 arxiv https arxiv org abs 1802 09502 acknowledgement the data from arxiv https arxiv org search advanced advanced 1 terms 0 operator and terms 0 term retrieval augmented terms 0 field title classification computer science y classification physics archives all classification include cross list include date filter by all dates date year date from date date to date date date type submitted date abstracts show size 200 order announced date first | large-language-models llm llms rag | ai |
SciSharp-Stack-Examples | scisharp stack examples this repo contains many practical examples written in scisharp s machine learning libraries if you still don t know how to use net for deep learning getting started from these examples is your best choice join the chat at https gitter im publiclab publiclab https badges gitter im join 20chat svg https gitter im sci sharp community requirements net core 5 0 https dotnet microsoft com download dotnet core 5 0 visual studio 2019 https visualstudio microsoft com vs or visual studio code https code visualstudio com run specific example in shell c bat run all examples from source code dotnet run project src tensorflownet examples run specific example dotnet run project src tensorflownet examples ex linear regression graph run in compiled library dotnet tensorflownet examples dll ex mnist cnn eager f bat run all examples from source code dotnet run project src tensorflownet examples fsharp run specific example dotnet run project src tensorflownet examples fsharp ex linear regression eager run in compiled library dotnet tensorflownet examples fsharp dll ex mnist cnn eager example runner will download all the required files like training data and model pb files basic model hello world c src tensorflownet examples helloworld cs f src tensorflownet examples fsharp helloworld fs basic operations c src tensorflownet examples basicoperations cs f src tensorflownet examples fsharp basicoperations fs linear regression in graph mode c src tensorflownet examples basicmodels linearregression cs f src tensorflownet examples fsharp basicmodels linearregression fs linear regression in eager mode c src tensorflownet examples basicmodels linearregressioneager cs f src tensorflownet examples fsharp basicmodels linearregressioneager fs linear regression in keras c src tensorflownet examples basicmodels linearregressionkeras cs logistic regression in graph mode c src tensorflownet examples basicmodels logisticregression cs f src tensorflownet examples fsharp basicmodels logisticregression fs logistic regression in eager mode c src tensorflownet examples basicmodels logisticregressioneager cs f src tensorflownet examples fsharp basicmodels logisticregressioneager fs nearest neighbor c src tensorflownet examples basicmodels nearestneighbor cs f src tensorflownet examples fsharp basicmodels nearestneighbor fs naive bayes classification c src tensorflownet examples basicmodels naivebayesclassifier cs f src tensorflownet examples fsharp basicmodels naivebayesclassifier fs k means clustering c src tensorflownet examples basicmodels kmeansclustering cs neural network full connected neural network in eager mode c src tensorflownet examples neuralnetworks fullyconnectedeager cs f src tensorflownet examples fsharp neuralnetworks fullyconnectedeager fs full connected neural network keras c src tensorflownet examples neuralnetworks fullyconnectedkeras cs f src tensorflownet examples fsharp neuralnetworks fullyconnectedkeras fs nn xor c src tensorflownet examples neuralnetworks neuralnetxor cs object detection in mobilenet c src tensorflownet examples objectdetection detectinmobilenet cs mnist fnn in keras functional api c src tensorflownet examples imageprocessing mnistfnnkerasfunctional cs f src tensorflownet examples fsharp imageprocessing mnistfnnkerasfunctional fs mnist cnn in graph mode c src tensorflownet examples imageprocessing digitrecognitioncnn cs f src tensorflownet examples fsharp imageprocessing digitrecognitioncnn fs mnist cnn in eager mode c src tensorflownet examples imageprocessing digitrecognitioncnneager cs f src tensorflownet examples fsharp imageprocessing digitrecognitioncnneager fs mnist cnn in keras subclass c src tensorflownet examples imageprocessing mnistcnnkerassubclass cs f src tensorflownet examples fsharp imageprocessing mnistcnnkerassubclass fs mnist rnn c src tensorflownet examples imageprocessing digitrecognitionrnn cs mnist lstm c src tensorflownet examples imageprocessing digitrecognitionlstm cs image classification in keras sequential api c src tensorflownet examples imageprocessing imageclassificationkeras cs f src tensorflownet examples fsharp imageprocessing imageclassificationkeras fs image recognition inception c src tensorflownet examples imageprocessing imagerecognitioninception cs f src tensorflownet examples fsharp imageprocessing imagerecognitioninception fs toy resnet in keras functional api c src tensorflownet examples imageprocessing toyresnet cs f src tensorflownet examples fsharp imageprocessing toyresnet fs transfer learning for image classification in inceptionv3 c src tensorflownet examples imageprocessing transferlearningwithinceptionv3 cs cnn in your own dataset c src tensorflownet examples imageprocessing cnninyourowndata cs f src tensorflownet examples fsharp imageprocessing cnninyourowndata fs natural language processing binary text classification c src tensorflownet examples textprocessing binarytextclassification cs cnn text classification c src tensorflownet examples textprocessing cnn models vdcnn cs named entity recognition c src tensorflownet examples textprocessing ner time series weather prediction cnn rnn c src tensorflownet examples timeseries weatherprediction cs welcome to pr your example to us your contribution will make net community better than ever br a href http scisharpstack org img src https github com scisharp scisharp blob master art scisharp stack png width 391 height 100 a | tensorflow tensorflow-examples scisharp csharp | ai |
Full-Stack-Web-Development-With-Flask | full stack web development with flask code snippets for the full stack web development with flask course available at pirple com this course is now available this course like all others is included with your pirple com monthly membership to join pirple visit our membership page here https pirple thinkific com pages membership https pirple thinkific com pages membership | front_end |
|
llm4data | llm4data llm4data is a python library designed to facilitate the application of large language models llms and artificial intelligence for development data and knowledge discovery it is intended to empower users and organizations to discover and interact with development data in innovative ways through natural language devdata chat https github com worldbank llm4data blob main img devdata chat png raw true the llm4data powers the devdata chat application which will soon be available as an open source project this application demonstrates the various ways in which llm language model and ai enhance discovery and interaction with data and knowledge bringing innovative solutions to help address discoverability and accessibility gaps the llm4data library contains a collection of discovery and data augmentation solutions for various data types including documents indicators microdata geospatial data and more the current version of the library includes solutions for the wdi indicators additional solutions will be added in future releases https worldbank github io llm4data readme html upcoming features built around existing metadata standards and schemas https mah0001 github io schema guide users and organizations can benefit from llms to enhance data driven applications enabling natural language processing text generation and more with llm4data the library serves as a bridge between llms and development data using open sourced libraries offering a seamless interface to leverage the capabilities of these powerful language models installation use the package manager pip https pip pypa io en stable to install llm4data bash pip install llm4data usage the following examples demonstrate how to use llm4data to generate wdi api urls and sql queries from prompts additional examples can be found here notebooks examples generate wdi api url from a prompt warning this example uses the openai api before you proceed make sure to set your api keys in the env file see the setup instructions https worldbank github io llm4data notebooks examples getting started openai api html for more details python from llm4data prompts indicators import wdi create a wdi api prompt object wdi api wdi wdiapiprompt send a prompt to the llm to get a wdi api url relevant to the prompt response wdi api send prompt what is the gdp and the co2 emissions of the philippines and its neighbors in the last decade parse the response to get the wdi api url wdi api url wdi api parse response response print wdi api url the output will look like the following https api worldbank org v2 country phl idn mys sgp tha vnm indicator ny gdp mktp cd en atm co2e kt date 2013 2022 format json source 2 notice that the url generated already includes the country codes and indicators relevant to the prompt it understands which countries are the neighbors of the philippines it also understands which indicator codes are likely to provide the relevant data for gdp and co2 emissions the url also includes the date range format and source of the data the user can then tweak the url as needed and use it to query the wdi api generate sql queries on wdi data from a prompt warning make sure you have set up your environment first the example below requires a working database engine e g postgresql if you want to use sqlite make sure to update the env file and set the environment variables while the wdi data can be loaded into a pandas dataframe it is not always practical to do so for example developing applications that can answer arbitrary data questions the llm4data library includes an sql interface to wdi data allowing users to query the data using sql this interface will allow users to query the data using sql and return the results as a pandas dataframe the interface also allows users to query the data using sql and return the results as a json object python import json from llm4data prompts indicators import templates wdi from llm4data llm indicators import wdi sql prompt what is the gdp and army spending of the philippines in 2020 sql data wdi sql wdisql llm2sql answer prompt as dict true print sql data sql select country value as gdp select value from wdi where country iso3 phl and indicator ms mil xpnd gd zs and year 2020 as army spending from wdi where country iso3 phl and indicator ny gdp mktp cd and year 2020 and value is not null params data data country philippines gdp 361751116292 541 army spending 1 01242392260698 sample country philippines gdp 361751116292 541 army spending 1 01242392260698 num samples 20 generate a narrative explanation of the sql query response the llm4data library also includes support for generating narrative explanations of sql query responses this is useful for generating natural language descriptions of data which can be used to provide context to users and to explain the results of data queries python from llm4data prompts indicators import templates send the prompt to the llm for a narrative explanation of the response this is optional and can be skipped note that we pass only a sample in the context data this could limit the quality of the response this is a limitation of the current version of the llm which is constrained by the context length and cost explainer templates indicatorprompt description explainer send prompt prompt prompt context data json dumps sql data data sample print description content based on the data provided the gdp of the philippines in 2020 was approximately 362 billion usd meanwhile the country s army spending in the same year was around 1 01 billion usd it is worth noting that while army spending is an important aspect of a country s budget it is not the only factor that contributes to its economic growth and development other factors such as infrastructure education and healthcare also play a crucial role in shaping a country s economy why not use langchain for sql queries langchain is a great library and it has a wrapper for sql databases that allows you to query them using natural language the wrapper is called sqldatabasechain and can be used as follows python from langchain import openai sqldatabase sqldatabasechain db sqldatabase from uri sqlite llm4dev data sqldb wdi db llm openai temperature 0 verbose true db chain sqldatabasechain from llm llm db verbose true return intermediate steps true out db chain what is the gdp and army spending of the philippines in 2020 bash entering new sqldatabasechain chain what is the gdp and army spending of the philippines in 2020 sqlquery select value from wdi where name gdp current us and country iso3 phl and year 2020 union select value from wdi where name military expenditure of gdp and country iso3 phl and year 2020 sqlresult 1 01242392260698 361751116292 541 answer the gdp of the philippines in 2020 was 1 01242392260698 and the military expenditure of gdp was 361751116292 541 finished chain unfortunately the answer the gdp of the philippines in 2020 was 1 01242392260698 and the military expenditure of gdp was 361751116292 541 is incorrect because the values have been swapped one of the goals of llm4data is to develop solutions around the limitations of existing open source solutions as applied to development data and knowledge discovery key features and roadmap text generation utilize llms to generate coherent and contextually relevant text around development data enabling the creation of chatbots and content generation systems interactive experiences create engaging user experiences by integrating llms into applications allowing users to interact with development data in a more intuitive and conversational manner metadata augmentation enhance existing metadata with llms enabling the creation of new metadata and the improvement of existing metadata ai powered insights extract valuable insights from datasets using llms empowering data exploration trend analysis and knowledge discovery dynamic integration through the use of metadata standards and schemas load and utilize your own python scripts containing llm functionality on the fly seamlessly incorporating them into your project through plug ins natural language processing leverage llms to analyze and process textual data enabling tasks like sentiment analysis text classification and language translation contributing pull requests are welcome for major changes please open an issue first to discuss what you would like to change please see contributing md github contributing md for more information license llm4data is licensed under the world bank master community license agreement license upcoming features metadata augmentation with llm document and metadata indexing semantic search for indicators for documents for microdata for geospatial data for voice and videos open source chat ui data use framework todo add contributing guidelines add more documentations add unit tests add ci cd | ai data gpt gpt-4 indicators llm metadata sql wdi world-development-indicators development-data llm4data | ai |
ChatGPT-at-Home | chatgpt at home chatgpt home large language model llm chatbot application written by chatgpt i asked chatgpt to build an llm based chatbot app and this was the result img src https pythonprogramming net static images chatgptathomesocial png width 512 | ai |
|
PLM | programmer s learning machine plm the programmer s learning machine plm is a platform dedicated to computer programming education this generic platform offers support to teachers for creating programming microworlds suitable to teaching courses it features an integrated and graphical environment providing a short feedback loop to students in order to improve the effectiveness of the autonomous learning process for more information visit the plm web site http people irisa fr martin quinson teaching plm or come and chat on our discord channel https discord gg agxnpgj license plm is licensed under the gnu general public license 3 this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 3 of the license or at your option any later version this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details you should have received a copy of the gnu general public license along with this program if not see http www gnu org licenses the documentation tutorial and source code are intended as a community resource and you can basically use copy and improve them however you want included works are subject to their respective licenses | ai |
|
machine-learning-mindmap | machine learning mindmap cheatsheet a mindmap summarising machine learning concepts from data analysis to deep learning overview machine learning is a subfield of computer science that gives computers the ability to learn without being explicitly programmed it explores the study and construction of algorithms that can learn from and make predictions on data machine learning is as fascinating as it is broad in scope it spans over multiple fields in mathematics computer science and neuroscience this is an attempt to summarize this enormous field in one pdf file download download the pdf here https github com dformoso machine learning mindmap blob master machine 20learning pdf same but with a white background https github com dformoso machine learning mindmap blob master machine 20learning 20 20white 20bg pdf i ve built the mindmap with mindnode for mac https mindnode com companion notebook this mindmap cheatsheet has a companion jupyter notebook that runs through most of the data science steps that can be found at the following link https github com dformoso sklearn classification mindmap on deep learning here s another mindmap which focuses only on deep learning https github com dformoso deeplearning mindmap 1 process the data science it s not a set and forget effort but a process that requires design implementation and maintenance the pdf contains a quick overview of what s involved here s a quick screenshot alt text https github com dformoso machine learning mindmap blob master images process png 2 data processing first we ll need some data we must find it collect it clean it and about 5 other steps here s a sample of what s required alt text https github com dformoso machine learning mindmap blob master images data 20processing png 3 mathematics machine learning is a house built on math bricks browse through the most common components and send your feedback if you see something missing alt text https github com dformoso machine learning mindmap blob master images mathematics png 4 concepts a partial list of the types categories approaches libraries and methodology alt text https github com dformoso machine learning mindmap blob master images concepts png 5 models a sampling of the most popular models send your comments to add more alt text https github com dformoso machine learning mindmap blob master images models png references i m planning to build a more complete list of references in the future for now these are some of the sources i ve used to create this mindmap stanford and oxford lectures cs20si cs224d books deep learning goodfellow pattern recognition and machine learning bishop the elements of statistical learning hastie colah s blog http colah github io kaggle notebooks tensorflow documentation pages google cloud data engineer certification materials multiple wikipedia articles about me twitter https twitter com danielmartinezf linkedin https www linkedin com in danielmartinezformoso email daniel martinez formoso gmail com | machine learning data science python jupyter cheatsheet mindmap machine-learning | ai |
ife | i of front end | front_end |
|
webvim | webvim resources webvim png v 2 webvim webvim is a vim based distribution targeting javascript and web development it targets javascript development es5 es6 node js html5 css3 and scss and contains the features you expect from a modern code editor syntax highlighting syntax and error checking autocompletion multi cursor git support code format support coding conventions editorconfig hardcore mode for real vim users emmet support jsdoc generation coming soon debugging coming soon grunt gulp support coming soon all the awesomeness from vim the webvim idea is to provide you a vim distribution something that comes prepackaged preconfigured built on a kernel to serve a goal webvim is to vim what debian is to linux a vim distribution for the web install only tested on linux dependencies the long story on ubuntu from 15 04 1 a modern version of vim sh apt get install vim vim runtime vim gui common or compile a recent version with xterm clipboard and ruby or python support 2 some tools to compile youcompleteme sh apt get install build essential cmake python dev exuberant ctags 3 node js and npm sh curl sl https deb nodesource com setup 0 12 bash apt get install y nodejs 4 some npm packages sh npm install g eslint csslint jshint jsonlint handlebars dependencies the short story please report me what you did to make it work on your os fedora 23 24 sh sudo dnf install cmake python devel npm vim npm install g npm eslint csslint jshint jsonlint handlebars install it sh git clone https github com krampstudio webvim git vim ln s vim vimrc vimrc ln s vim tern project tern project vim the plugins install can take some times especially since there s a compilation made by youcompleteme if you ve the feeling the install has frozen you can finish the install after by entering the command pluginstall hardcore mode the hardcore mode remap some keys to force you use vim in a productive way no arrow keys for moving instead use the common vim movement commands in insert mode use jk to switch back to normal mode instead of esc restricting commands is the best way to make your fingers learn after one or two days you should be more productive and have learned lots of vim commands you can disable the hardcore mode by setting the value of g hardcoremode to 0 in vimrc you can also change the mappings usage vim webvim is only a vim distribution with plugins and configuration so all common vim commands and basic mapping are available you must know how to use vim before using this ide if you re not comfortable with vim enough i suggest you to take the interactive vim tutorial run vimtutor in a terminal and keep a common usage cheat sheet http fprintf net vimcheatsheet html close to you until your fingers get all the mappings in memory webvim command mode context plugins install plugins pluginstall n update plugins plugupdate n config edit vimrc leader ev n reload vimrc leader sv n file tree nerdtree toggle tree c n n open a node in a new tab t tree node change root c tree node tree menu m tree node add a file a tree menu delete a file d tree menu move a file m tree menu copy a file c tree menu search in files grep g tree menu next match in grep cn grep quickfix move to left tab s left n move to right tab s right n change window ie tree to tab c w c w help tree documentation help nerdtree comment toggle comments c nv comments leader cc nv sexy comments leader cs nv uncomments leader cu nv yank and comments leader cy nv documentation help nerdcommenter align start interactive alignment easyalign v selection align next paragraph on leader a n align next paragraph on leader a n align next paragraph on delimiter x leader ax n right align selection on leader a v right align selection on leader a v right align selection on x leader ax v documentation help easyalign format format the file c f n js json html css format the selection c f n js json html css multiple cursor start multiple cursor c m v visual block multiple cursor insert i multiple cursor multiple cursor remove x multiple cursor leave multiple cursor esc multiple cursor paste cycle backward through your history of yanks leader p nv after paste p cycle forward through your history of yanks leader p nv after paste p autocompletion select next proposal in menu tab i complete menu select previous proposal in menu shift tab i complete menu syntax checking checkers infos syntasticinfo n check syntasticcheck n toggle check syntastictogglemode n error window errors n jump next error lnext n jump previous error lprev n javascript get type leader gt n under cursor get documentation leader gd n under cursor go to leader go n under cursor jump to definition leader gf n under cursor go to references leader gr n under cursor rename leader r n under cursor jump to the source of a require gf n node js cursor edit the main file of a cjs module nedit module n node js edit a file of a cjs module nedit module foo js n node js edit projects main from package json nedit n node js git git diff gdiff n git status gstatus n git commit gcommit n git blame gblame n git mv gmove n git rm gremove n open the current file in github gbrowse n spell check enable checking set spell n move to the next misspelled word s n move to the previous misspelled word s n add a word to the dictionary zg n undo the addition of a word to the dictionary zug n view spelling suggestions for a misspelled word z n search clear highlights c l n editing move line up leader nv move line down leader nv wrap in single quote leader nv wrap in double quote leader nv emmet expand abbreviation c k i html css scss next sections to come soon modes n normal i insert v visual commands command a vim command set something can also be replaced by setlocal something to apply it to the current buffer only c m a or a a keyboard command c means ctrl and this is the vim notation s left means shift and left arrow c a b means ctrl and a then b leader is mapped to localleader is mapped to plugins webvim is only a distribution that contains plugins the plugin authors have made the hard work plugin authors rocks plugin vim plug https github com junegunn vim plug minimalist vim plugin manager user interface mango https github com goatslacker mango vim a nice color scheme vimairline https github com bling vim airline lean and mean statusbars manage your project nerdtree https github com scrooloose nerdtree manage your project files vimfugitive https github com tpope vim fugitive git integration vimgitgutter https github com airblade vim gitgutter git diff in the gutter editorconfigvim https github com editorconfig editorconfig vim shared coding conventions code writing nerdcommenter https github com scrooloose nerdcommenter comments made easy vimtrailingwhitespace https github com bronson vim trailing whitespace highlight trailing spaces syntastic https github com scrooloose syntastic syntax check and validation vimeasyalign https github com junegunn vim easy align realign pieces of code vimmultiplecursors https github com terryma vim multiple cursors write on multiple lines easily vimjsbeautify https github com maksimr vim jsbeautify reformat javascript html and json files vimyankstack https github com maxbrunsfeld vim yankstack iterate over yanked stack on paste vimsurround https github com tpope vim surround quoting and parenthesizing youcompleteme https github com valloric youcompleteme autocompletion engine vimnode https github com moll vim node navigate through node js code modules vimlint https github com syngan vim vimlint linter used by syntastic for viml vimlparser https github com ynkdir vim vimlparser viml parser required by vimlint emmet vim https github com mattn emmet vim expanding abbreviations similar to emmet http emmet io code reading vimjson https github com elzr vim json json highlighting and quote concealing yajs https github com othree yajs vim javascript syntax es5 and es6 javascriptlibrariessyntax https github com othree javascript libraries syntax vim syntax highlighting for well known js libraries vimcss3 https github com hail2u vim css3 syntax css3 syntax scsssyntax https github com cakebaker scss syntax vim scss syntax html5 https github com othree html5 vim html5 syntax history 1 3 0 fixed dependencies tern via ycm emmet new theme nerdtree grep use local linters 1 2 0 fix 28 support new esint config files update installe 1 1 0 add user config autocmd file fix easyalign mapping update nerdtree config better mouse support in insert mode 1 0 0 becomes webvim with an install process a better configuration system better plugins neighborhood 0 1 0 a basic dotvim repository with my own vim configuration contributing every contribution is more than welcomed you can report issues https github com krampstudio webvim issues fix improve the configuration add new features the best is to fork and submit a pull request test and adapt to other os fix my english mistakes update the documentation create a better logo offer me a coffee https liberapay com krampstudio donate donate using liberapay https liberapay com assets widgets donate svg https liberapay com krampstudio donate license the content of this repository is licensed under the gplv3 http www gnu org licenses gpl 3 0 txt | front_end |
|
rtosDiagrams | rtosdiagrams images showing real time operating system rtos concepts and functionality these diagrams were made to illustrate concepts in the book hands on rtos with microcontrollers https www amazon com hands rtos microcontrollers building real time dp 1838826734 dp 1838826734 ref mt other encoding utf8 me qid example code for the book can be downloaded for free at https github com packtpublishing hands on rtos with microcontrollers all images and diagrams in this repository are licensed under cc by 4 0 feel free to use modify them however you like but please include attribution to brian amos all of the diagrams were created with https www draw io so if you d like to modify something try using draw io to open the file i m including the draw io source in the png files which allows opening the png file in draw io for modification or directly including the same file and open as a standard image this functionality might come in handy if someone happens to run across one of the images and also uses draw io they d get a pleasant surprise to find out that the image is directly editable it also makes for an easier workflow since the png files can simply be exported from draw io then i only need to keep track of one version of the file instead of figuring out whether the exported png is up to date with the drawio | os |
|
tokenlists | multi chain token list standard tldr in this repo you may find tokenlists aggregated from various trusted providers such as sushiswap or 1inch we only list a token if it appeared in 2 or more different tokenlists so we believe that if 2 or more providers list a token than it is most likely not a scam usage example if you want to use tokenlist in your dapp simply download json with needed chain tokens head for raw link like https raw githubusercontent com viaprotocol tokenlists main tokenlists ethereum json ethereum tokenlist or https raw githubusercontent com viaprotocol tokenlists main tokenlists bsc json binance smart chain tokenlist providers we collect tokenlists from github repos or open apis from various platforms currently coingecko https www coingecko com 1inch https app 1inch io uniswap https uniswap org sushiswap https www sushi com openocean https openocean finance solanalabs https solanalabs com elkfinance https elk finance onesol https 1sol io quickswap https quickswap exchange swap fuseswap https beta fuseswap com swap trisolarislabs https www trisolaris io swap rubic https app rubic exchange feel free to add new provider if you think it is trusted and if it has opensource tokenlists on github or in api chains with trusted tokens here are chains presented in our tokenlists with current token count you can find out more in tokenlists folder token counts are approximate and may vary as providers update their tokenlists ethereum 1531 tokens bsc 1004 tokens polygon 681 tokens 101 507 tokens solana 394 tokens avax 359 tokens ftm 321 tokens gnosis 285 tokens heco 197 tokens arbitrum 178 tokens optimism 101 tokens aurora 86 tokens harmony 76 tokens cronos 68 tokens celo 68 tokens moonriver 61 tokens okex 48 tokens moonbeam 34 tokens fuse 23 tokens evmos 21 tokens astar 15 tokens boba 13 tokens telos 10 tokens kcc 9 tokens testnets rinkeby ropsten goerli mumbai etc how are tokenlists formed we collect many tokenlists from many providers then we aggregate them by chains and tokens addresses for each token we check whether it is listed in 2 or more tokenlists from different providers if so we add it to our trusted tokenlist run aggregation script yourself install requirements pip3 install r requirements txt run the script from repo root folder python3 aggregate tokens py generate readme md based on aggregated data bash python generate readme py contribute feel free to open issues and prs with tokens chains or providers that you want to add developed by via exchange https via exchange team | tokenlist ethereum binance-smart-chain polygon solana arbitrum optimism avalanche celo fantom gnosis kcc moonbeam moonriver okex telos | blockchain |
TemperatureSensor | temperaturesensor converting raw temperature data to engineering units calibrating the temperature and uploading it to database along with timestamp | server |
|
universal | universal a header only c template library for universal number arithmetic system status more information codacy code quality https app codacy com gh stillwater sc universal dashboard codacy badge https api codacy com project badge grade 25452f0319d34bc2a553cd1857d7dfae https app codacy com gh stillwater sc universal utm source github com utm medium referral utm content stillwater sc universal utm campaign badge grade dashboard code quality assessment fossa status https app fossa com projects git 2bgithub com 2fstillwater sc 2funiversal fossa status https app fossa com api projects git 2bgithub com 2fstillwater sc 2funiversal svg type shield https app fossa com projects git 2bgithub com 2fstillwater sc 2funiversal ref badge shield open source license dependency scanner github actions https github com stillwater sc universal actions build status https github com stillwater sc universal actions workflows cmake yml badge svg branch main https github com stillwater sc universal latest linux macos windows builds and regression tests development branch https github com stillwater sc universal actions development branch status https github com stillwater sc universal actions workflows cmake yml badge svg branch v3 61 development branch regression status https github com stillwater sc universal actions regression status https github com stillwater sc universal actions workflows cmake yml badge svg event push regression status code coverage https coveralls io coverage status https coveralls io repos github stillwater sc universal badge svg branch main https coveralls io github stillwater sc universal branch main code coverage scanner docker pulls https hub docker com r stillwater universal docker pulls https img shields io docker pulls stillwater universal svg https hub docker com r stillwater universal container pulls awesome c https github com fffaraz awesome cpp awesome cpp https awesome re mentioned badge svg https github com fffaraz awesome cpp math awesome c libraries joss markdown https joss theoj org status https joss theoj org papers 932fdfc2735a85422e4431f27ebfc0d0 status svg https joss theoj org papers 932fdfc2735a85422e4431f27ebfc0d0 journal of open source software paper zenodo https zenodo org record 7735084 doi https zenodo org badge doi 10 5281 zenodo 7735084 svg https doi org 10 5281 zenodo 7735084 zenodo doi badge the goal of the universal numbers library is to offer alternatives to native integer and floating point for mixed precision algorithm development and optimization tailoring the arithmetic types to the application s precision and dynamic range enables a new level of application performance and energy efficiency particularly valuable for embedded applications that need autonomy through intelligent behavior deep learning algorithms in particular provide a core application vertical where alternative formats and precisions such as half precision floating point and bfloat16 yield speed ups of two to three orders of magnitude making rapid innovation in ai possible the universal library is a ready to use header only library that provides a plug in replacement for native types and offers a low friction environment to explore alternatives to ieee 754 floating point in ai dsp hpc and hft algorithms the basic use pattern is as simple as code bring in the parameterized type of interest in this case a fixed sized arbitrary configuration classic floating point include universal number cfloat cfloat hpp define your computational kernel parameterized by arithmitic type template typename real real mykernel const real a const real b return a b replace this with your kernel computation constexpr double pi 3 14159265358979323846 int main if desired create an application type alias to avoid errors using real sw universal half half precision ieee 754 floating point real a sqrt 2 real b pi finally call your kernel with your desired arithmetic type std cout result mykernel a b std endl the library contains fast implementations of special ieee 754 formats that do not have universal hardware implementations across x86 arm power risc v and gpus special formats such as quarter precision quarter half precision half and quad precision quad are provided as well as vendor specific extensions such as nvidia tensorfloat google s brain float bfloat16 or ti dsp fixed points fixpnt in addition to these often used specializations universal supports static and elastic integers decimals fixed points rationals linear floats tapered floats logarithmic interval and adaptive precision integers rationals and floats there are example number system skeletons to get you started quickly if you desire to add your own communication channels github issue https github com stillwater sc universal issues bug reports feature requests etc forum https groups google com u 1 g unum computing discussion of alternatives to ieee 754 for computational science slack https fptalks slack com online chats discussions and collaboration with other users researchers and developers citation please cite our work https arxiv org abs 2012 11011 if you use universal bib article omtzigt2023universal title universal numbers library multi format variable precision arithmetic library author omtzigt e theodore l and quinlan james journal journal of open source software volume 8 number 83 pages 5072 year 2023 inproceedings omtzigt 2022 title universal reliable reproducible and energy efficient numerics author e theodore l omtzigt and james quinlan booktitle conference on next generation arithmetic pages 100 116 year 2022 organization springer article omtzigt2020 author e theodore l omtzigt and peter gottschling and mark seligman and william zorn title universal numbers library design and implementation of a high performance reproducible number systems library journal arxiv 2012 11011 year 2020 talks and presentations the following presentations describe universal and the number systems it contained as of the time of publication slides of a presentation at fptalks 21 https fpbench org talks fptalks21 html presentation application driven custom number systems https drive google com file d 1fpvj5kjjnky9tivcbx8xwb5czgnd87dr view slides of the presentation at conga 22 https link springer com book 10 1007 978 3 031 09779 9 presentation universal reliable reproducible and energy efficient numerics docs presentations conga22 universal arithmetic library pdf a quick description of the structure of the number system parameterization can be found here docs number system type parameterization md quick start if you just want to experiment with the number system tools and test suites and don t want to bother cloning and building the source code there is a docker container to get started text docker pull stillwater universal docker run it rm stillwater universal bash stillwater b3e6708fd732 universal build ls cmakecache txt makefile cmake uninstall cmake playground universal config version cmake cmakefiles applications cmake install cmake tests universal config cmake ctesttestfile cmake c api education tools universal targets cmake here docs command line tools md is a quick reference of what the command line tools have to offer how to build if you do want to work with the code the universal numbers software library is built using cmake version v3 23 install the latest cmake https cmake org download there are interactive installers for macos and windows for linux a portable approach downloads the shell archive and installs it at usr local text wget https github com kitware cmake releases download v3 23 1 cmake 3 23 1 linux x86 64 sh sudo sh cmake 3 23 1 linux x86 64 sh prefix usr local exclude subdir for ubuntu snap will install the latest cmake and would be the preferred method text sudo snap install cmake classic the universal library is a pure c template library without any further dependencies even for the regression test suites to enable hassle free installation and use clone the github repo and you are ready to build the different components of the universal library the library contains tools for using integers decimals fixed points floats posits valids and logarithmic number systems it includes educational programs that showcase simple use cases to familiarize yourself with different number systems and application examples to highlight the use of other number systems to gain performance or numerical accuracy finally each number system offers its own verification suite the easiest way to become familiar with all the options in the build process is to fire up the cmake gui or ccmake if you are on a headless server the cmake output will summarize which options have been set the output will look something like this text git clone https github com stillwater sc universal cd universal mkdir build cd build cmake the c compiler identification is gnu 9 4 0 the cxx compiler identification is gnu 9 4 0 the asm compiler identification is gnu found assembler usr bin cc detecting c compiler abi info detecting c compiler abi info done check for working c compiler usr bin cc skipped detecting c compile features detecting c compile features done detecting cxx compiler abi info detecting cxx compiler abi info done check for working cxx compiler usr bin c skipped detecting cxx compile features detecting cxx compile features done no default build type specified setting cmake build type release c 20 has been enabled by default performing test compiler has sse3 flag performing test compiler has sse3 flag success performing test compiler has avx flag performing test compiler has avx flag success performing test compiler has avx2 flag performing test compiler has avx2 flag success project name universal project name nospaces universal project source dir home stillwater dev clones universal project version 3 68 1 80df9073 cmake c compiler usr bin cc cmake cxx compiler usr bin c cmake current source dir home stillwater dev clones universal cmake current binary dir home stillwater dev clones universal build gcc git commit hash 80df9073 git branch v3 68 include install dir include include install dir full include universal config install dir share universal include install dir postfix universal universal arithmetic library configuration summary general version 3 68 1 80df9073 system linux c language requirement c 20 c compiler usr bin cc release c flags o3 dndebug wall wpedantic wno narrowing wno deprecated debug c flags g wall wpedantic wno narrowing wno deprecated c compiler usr bin c release cxx flags o3 dndebug wall wpedantic wno narrowing wno deprecated wall wpedantic wno narrowing wno deprecated debug cxx flags g wall wpedantic wno narrowing wno deprecated wall wpedantic wno narrowing wno deprecated build type release build all off build ci off build demonstration on build numbers off build numerics off build benchmarks off build mixedprecision sdk off build cmd line tools on build education on build applications on build playground on build number internals off build number native types off build number elastics off build number statics off build number conversions off build number eintegers off build number decimals off build number rationals off build number efloats off build number eposits off build number integers off build number fixpnts off build number bfloats off build number cfloats off build number dfloats off build number areals off build number unum1s off build number unum2s off build number posits off build number valids off build number lns off build number lns2b off build number sorns off build numeric functions off build numeric quires off build numeric challenges off build numeric utils off build numeric fpbench off build benchmark error off build benchmark accuracy off build benchmark reproducibility off build benchmark performance off build benchmark energy off build mixedprecision roots off build mixedprecision approximate off build mixedprecision integrate off build mixedprecision interpolate off build mixedprecision optimize off build mixedprecision tensor off build linear algebra blas off build linear algebra vmath off build c api pure lib off build c api shim lib off build c api lib pic off build docs off regression testing level build regression sanity on dependencies sse3 no avx no avx2 no pthread no tbb no omp no utilities serializer no install install path usr local configuring done generating done as you can see in the cmake output there are many build targets each build target is designed to provide focus and fast build turnarounds when working with different number systems each number system has its own build target allowing fast and efficient regression testing the build options are enabled disabled as follows text cmake dbuild education off dbuild number posits on after building issue the command make test to run the complete test suite of all the enabled components as a regression capability when you are modifying the source code this will take touch all the corners of the code text git clone https github com stillwater sc universal cd universal mkdir build cd build cmake make j nproc make test for windows and visual studio there are cmakepredefinedtargets that accomplish the same tasks text all build will compile all the projects install will install the universal library run tests will run all tests here is the layout of all the projects contained in v3 68 of universal visual studio project docs img visual studio project png in the applications section you will find application examples to demonstrate the use of universal arithmetic types to accomplish different numerical goals such as reproducibility accuracy performance or precision these examples are great starting points for your own application requirements example applications docs img example applications png how to develop and extend universal the universal library contains hundreds of example programs to demonstrate the use of the arithmetic types and the enable new developers to get up to speed in each number system type s regression suite there is an api api cpp that chronicles all the invokation and use cases to provide an executable example of how to use the type in general the api section of the regression tests has code examples how to use the different library components such as manipulators attributes number traits exceptions and special cases in the education build target build education there are individual test programs that demonstrate how to use the different types the docs directory contains the descriptions of the command line tools docs command line tools md a tutorial docs number system type parameterization md explaining the parameterization design of the arithmetic types in universal several conference presentations fptalks docs presentations fptalks custom number systems pdf and conga22 docs presentations conga22 universal arithmetic library pdf describing the arithmetic types the docs directory also contains ready to use value tables and dynamic range comparisons of many key small arithmetic types of interest in ai and dsp applications each number system comes with a complete regression suite to verify the functionality of assignment conversion arithmetic logic exceptions number traits and special cases these regression suites are run for each pr or push to the version branch universal uses standard github actions for this so add your branch to the workflow cmake yaml to trigger ci for your own branch the easiest way to get started is to pick up and copy the directory structure under root include universal number skeleton 1param or root include universal number skeleton 2params they are configured to get you all the constituent pieces of a number system universal style installation and usage after cloning the library building and testing it in your environment you can install it via text cd universal build cmake dcmake install prefix path your installation path cmake build config release target install j nproc or manually via the makefile target in the build directory text make j nproc install the default install directory is usr local under linux there is also an uninstall command text make uninstall if you want to use the number systems provided by universal in your own project you can use the following cmakelists txt structure code project my numerical experiment find package universal config required add executable project name src mymain cpp set property target project name property cxx standard 17 target link libraries project name universal universal controlling the build to include different components the default build configuration will build the command line tools a playground educational and application examples if you want to build the full regression suite across all the number systems use the following cmake command text cmake dbuild all on for performance the build configuration can enable specific x86 instruction sets sse avx avx2 for example if your processor supports the avx2 instruction set you can build the test suites and educational examples with the avx2 flag turned on this typically yields a 20 performance boost text cmake dbuild all on duse avx2 on the library builds a set of useful command utilities to inspect native ieee float double long double types as well as the custom number systems provided by universal assuming you have build and installed the library the inspection commands available are text ieee show the components of the full set of ieee floating point values quarter show the components and traits of a quarter precision floating point value fp8 half show the components and traits of a half precision ieee 754 value fp16 single show the components and traits of a single precision ieee 754 value fp32 double show the components and traits of a double precision ieee 754 value fp64 longdouble show the components and traits of a native long double ieee 754 value quad show the components and traits of a quad precision ieee 754 value fp128 signedint show the components and traits of a signed integer value unsignedint show the components and traits of an unsigned integer value fixpnt show the components and traits of a fixed point value posit show the components and traits of a posit value lns show the components and traits of a logarithmic number system value float2posit show the conversion process of a real value to a posit propenv show the properties of the execution compiler environment that built the library propp show numerical properties of a posit environment including the associated quire propq show numerical properties of a quire for example text ieee 1 234567890123456789012 compiler 7 5 0 float precision 23 bits double precision 52 bits long double precision 63 bits decimal representations input value 1 23456789012 float 1 23456788 double 1 2345678901199999 long double 1 23456789011999999999 hex representations input value 1 23456789012 float 1 23456788 hex 0 7f 1e0652 double 1 2345678901199999 hex 0 3ff 3c0ca428c1d2b long double 1 23456789011999999999 hex 0 3fff 1e06521460e95b9a binary representations float 1 23456788 bin 0 01111111 00111100000011001010010 double 1 2345678901199999 bin 0 01111111111 0011110000001100101001000010100011000001110100101011 long double 1 23456789011999999999 bin 0 011111111111111 001111000000110010100100001010001100000111010010101101110011010 native triple representations sign scale fraction float 1 23456788 triple 0 00111100000011001010010 double 1 2345678901199999 triple 0 0011110000001100101001000010100011000001110100101011 long double 1 23456789011999999999 triple 0 001111000000110010100100001010001100000111010010101101110011010 universal triple representation sign scale fraction input value 1 23456789012 float 1 23456788 triple 0 00111100000011001010010 double 1 2345678901199999 triple 0 0011110000001100101001000010100011000001110100101011 long double 1 23456789011999999999 triple 0 001111000000110010100100001010001100000111010010101101110011010 exact tbd this ieee command is very handy to quickly determine how your development environment represents truncates a specific value the specific commands single double and longdouble focus on float double and long double representations respectively there is also a command posit to help you visualize and compare the posit component fields for a given value for example text posit 1 234567890123456789012 posit 8 0 s0 r10 e f01000 qne v1 25 posit 8 1 s0 r10 e0 f0100 qne v1 25 posit 8 2 s0 r10 e00 f010 qne v1 25 posit 8 3 s0 r10 e000 f01 qne v1 25 posit 16 1 s0 r10 e0 f001111000001 qne v1 234619140625 posit 16 2 s0 r10 e00 f00111100000 qne v1 234375 posit 16 3 s0 r10 e000 f0011110000 qne v1 234375 posit 32 1 s0 r10 e0 f0011110000001100101001000011 qne v1 2345678918063641 posit 32 2 s0 r10 e00 f001111000000110010100100001 qne v1 2345678880810738 posit 32 3 s0 r10 e000 f00111100000011001010010001 qne v1 2345678955316544 posit 48 1 s0 r10 e0 f00111100000011001010010000101000110001011010 qne v1 2345678901234578 posit 48 2 s0 r10 e00 f0011110000001100101001000010100011000101101 qne v1 2345678901234578 posit 48 3 s0 r10 e000 f001111000000110010100100001010001100010110 qne v1 2345678901233441 posit 64 1 s0 r10 e0 f001111000000110010100100001010001100010110011111101100000000 qne v1 2345678901234567 posit 64 2 s0 r10 e00 f00111100000011001010010000101000110001011001111110110000000 qne v1 2345678901234567 posit 64 3 s0 r10 e000 f0011110000001100101001000010100011000101100111111011000000 qne v1 2345678901234567 the fields are prefixed by their first characters for example posit 16 2 s0 r10 e00 f00111100000 qne v1 234375 sign field s0 indicating a positive number regime field r10 indicates the first positive regime named regime 0 exponent field e00 indicates two bits of exponent both 0 fraction field f00111100000 a full set of fraction bits the field values are followed by a quadrant descriptor and a value representation in decimal qne north east quadrant representing a number in the range 1 maxpos v1 234375 the value representation of the posit projection the positive regime for a posit shows a very specific structure as can be seen in the image blow regime structure docs img positive regimes png leveraging the universal library in your own mixed precision algorithm research to bootstrap any new mixed precision algorithm development and optimization project quickly and robustly there is a github template repo available that will set up a complete working development environment with dependent libraries development containers vs code integration and a github ci workflow the template repo can be found at mpadao template https github com stillwater sc mpadao template the template repo is the easiest way to get started with mixed precision algorithm development using universal motivation modern deep learning ai applications are very demanding high performance applications runtimes to train models are measured in terms of weeks and target latencies for inference are 10 100msec standard double and even single precision ieee 754 floating point have been too expensive to use in addressing the performance and power requirements of ai applications in both the cloud and the edge both google and microsoft have jettisoned traditional floating point formats for their ai cloud services to gain two orders of magnitude better performance similarly ai applications for mobile and embedded applications are requantized to small integers to fit their very stringent power budgets the ai domain has been researching better number systems to address both power and performance requirements but all these efforts have worked in isolation with results being difficult to reproduce ai applications are only some of the applications that expose the limitations of traditional hardware inefficiencies in numeric storage and operations also limit cloud scale iot embedded and hpc applications a simple change to a new number system may improve the scale and cost of these applications by orders of magnitude when performance and power efficiency are the differentiating attributes for a use case arithmetic systems that are tailored to the needs of the application are desired in particular there are two concerns when using the ieee 754 floating point formats inefficient representation of the real numbers irreproducibility in the context of concurrency more specifically 1 wasted bit patterns 32 bit ieee floating point has around eight million ways to represent nan not a number while the 64 bit floating point has two quadrillion which is approximately 2 251x10 15 to be more exact a nan is an exceptional value to represent undefined or invalid results such as the result of a division by zero 2 mathematically incorrect the format specifies two zeroes a negative and positive zero with different behaviors loss of associative and distributive law due to rounding after each operation this loss of associative and distributive arithmetic behavior creates an irreproducible result of concurrent programs that use the ieee floating point this is particularly problematic for embedded and control applications 3 overflows to inf and underflows to 0 overflowing to inf increases the relative error by an infinite factor while underflowing to 0 loses sign information 4 unused dynamic range the dynamic range of double precision floats is a whopping 2 2047 whereas most numerical software is architected to operate around 1 0 5 complicated circuitry denormalized floating point numbers have a hidden bit of 0 instead of 1 this creates a host of special handling requirements that complicate compliant hardware implementations 6 no gradual overflow and fixed accuracy if accuracy is defined as the number of significand bits ieee floating point has fixed accuracy for all numbers except denormalized numbers because the number of signficand digits is fixed denormalized numbers are characterized by decreased significand digits when the value approaches zero due to having a zero hidden bit denormalized numbers fill the underflow gap i e between zero and the least non zero values the counterpart for gradual underflow is gradual overflow which does not exist in ieee floating points in contrast the posit number system was designed to overcome these negatives 1 economical no bit patterns are redundant there is one representation for infinity denoted as inf and zero all other bit patterns are valid distinct non zero real numbers inf serves as a replacement for nan 2 preserves mathematical properties there is only one representation for zero and the encoding is symmetric around 1 0 associative and distributive laws are supported through deferred rounding via the quire enabling reproducible linear algebra algorithms in any concurrency environment 3 tapered accuracy tapered accuracy is when values with small exponents have more precision and values with large exponents have fewer digits of accuracy this concept was first introduced by morris 1971 in his paper tapered floating point a new floating point representation 4 parameterized precision and dynamic range posits are defined by a size nbits and the number of exponent bits es this enables system designers the freedom to pick the right precision and dynamic range required for the application for example we may pick 5 or 6 bit posits without any exponent bits for ai applications to improve performance for embedded dsp applications such as 5g base stations we may select a 16 bit posit with one exponent bit to improve performance per watt 5 simpler circuitry there are only two exceptional cases not a real and zero no denormalized numbers overflow or underflow however as deep learning has demonstrated there are many different requirements to optimize an arithmetic and tailor it to the needs of the application universal brings all the machinery together to experiment to facilitate efficient contrast and compare different arithmetic number system designs before committing them to hardware goals of the library the universal library started as a bit level arithmetic reference implementation of the evolving unum type iii posit and valid standard however the demands for supporting number systems such as adaptive precision integers to solve large factorials adaptive precision floats to act as oracles or comparing linear and tapered floats provided the opportunity to create a complete platform for numerical analysis and computational mathematics with this universal platform we enable a new direction for optimizing algorithms to take advantage of mixed precision computation to maximize performance and minimize energy demands energy efficiency is going to be the key differentiator for embedded intelligence applications as a reference library universal offers an extensive test infrastructure to validate number system arithmetic operations and there is a host of utilities to inspect the internal encodings and operations of the different number systems the design space for custom arithmetic is vast and any contribution to expanding the capability of the universal library is encouraged contributing to universal we are happy to accept pull requests via github the only requirement is that the entire regression test suite passes stargazers over time https starchart cc stillwater sc universal svg https starchart cc stillwater sc universal verification suite typically the verification suite is run as part of the build directory s make test command however it is possible to run specific test suite components for example to validate algorithmic changes to more complex arithmetic functions such as square root exponent logarithm and trigonometric functions here is an example text dev universal build make posit logarithm 50 building cxx object static posit cmakefiles posit logarithm dir math logarithm cpp o 100 linking cxx executable posit logarithm 100 built target posit logarithm dev universal build static posit posit logarithm posit logarithm function validation results only 4 log 4 1 3862943649292 0110000000000000 log 4 0100011000101110 reference 0100011000101110 pass posit 2 0 log pass posit 3 0 log pass posit 3 1 log pass posit 4 0 log pass posit 4 1 log pass posit 5 0 log pass posit 5 1 log pass posit 5 2 log pass posit 8 4 log pass posit 8 4 log2 pass posit 8 4 log10 pass posit logarithm function validation pass structure of the tree the universal library contains a set of functional groups to organize the development and validation of different number systems each number system type has a single include file that brings together the arithmetic number type and all the extensions that universal has standardized so that working with numeric types is more productive for example facilities for number traits an arithmetic exception hierarchy number system attributes manipulators and finally a math library specialized for the type the number system types are categorized as static or elastic static types are arithmetic types that have a constant that is static size and thus can be used for sharing composite data structures such as matrices and tensors between general purpose cpus and special purpose hardware accelerators elastic types are arithmetic types that can grow and shrink during computation typically to accommodate error free or closed computations in addition to the static and elastic classification we also recognize that the base of the number system is a key parameter in the arithmetic and numerical traits of the type in particular the tree will specialize in binary and decimal forms of arithmetic here is a complete list static fixed sized configurations universal number integer arbitrary configuration fixed size integer universal number fixpnt arbitrary configuration fixed size fixed point number system universal number areal arbitrary configuration fixed size faithful floating point with uncertainty bit universal number cfloat arbitrary configuration fixed size classic floating point number system universal number posit arbitrary configuration fixed size posit number system a tapered floating point universal number valid arbitrary configuration fixed size valid number system a tapered floating point interval number system universal number unum arbitrary configuration unum type 1 number system universal number unum2 arbitrary configuration unum type 2 number system universal number lns arbitrary configuration logarithmic number system with fixed point exponent universal number dbns double base number system with integer exponents universal number sorn set of real numbers elastic adaptive precision configurations universal number decimal adaptive precision decimal integer universal number einteger adaptive precision binary integer universal number rational adaptive precision rational number system universal number efloat adaptive precision linear floating point universal number eposit adaptive precision tapered floating point super accumulator facilities universal number quire arbitrary configuration fixed size super accumulator number system add sub abs sqrt universal number float contains the implementation of the ieee floating point augmentations for reproducible computation and each of these functionality groups has an associated test suite located in universal tests background information universal numbers unums for short express real numbers and ranges of real numbers there are two modes of operation selectable by the programmer posit mode and valid mode in posit mode a unum behaves like a floating point number of fixed size rounding to the nearest expressible value if the result of a calculation is not expressible exactly a posit offers more accuracy and a wider dynamic range than floats with the same number of bits in valid mode a unum represents a range of real numbers and can be used to bound answers rigorously much as interval arithmetic does posit configurations have a specific relationship to one another when expanding a posit the new value falls between the old values of the smaller posit the new value is the arithmetic mean of the two numbers if the expanding bit is a fraction bit and it is the geometric mean of the two numbers if the expanding bit is a regime or exponent bit this page docs positrefinementviz md shows a visualization of the expansion of posit 2 0 to posit 7 1 public domain and community resources the unum format is a public domain specification and a collection of web resources to manage information and discussions using unums posit hub https posithub org unum computing google group https groups google com forum forum unum computing projects that leverage posits matrix template library http simunova com en mtl4 index html the matrix template library incorporates modern c programming techniques to provide an easy and intuitive interface to users while enabling optimal performance the natural mathematical notation in mtl4 empowers all engineers and scientists to implement their algorithms and models in minimal time all technical aspects are encapsulated in the library think of it as matlab for applications g smo http gs jku at gismo g smo geometry simulation modules pronounced gismo is a new open source c library that brings together mathematical tools for geometric design and numerical simulation it is developed mainly by researchers and phd students it implements the relatively new paradigm of isogeometric analysis which suggests the use of a unified framework in the design and analysis pipeline g smo is an object oriented cross platform template c library and follows the generic programming principle with a focus on both efficiency and ease of use the library is partitioned into smaller entities called modules examples of available modules include the dimension independent nurbs module the data fitting and solid segmentation module the pde discretization module and the adaptive spline module based on hierarchical splines of arbitrary dimension and polynomial degree fenics https fenicsproject org fenics is a popular open source lgplv3 computing platform for solving partial differential equations pdes fenics enables users to quickly translate scientific models into efficient finite element code with the high level python and c interfaces to fenics it is easy to get started but fenics offers also powerful capabilities for more experienced programmers fenics runs on a multitude of platforms ranging from laptops to high performance clusters odeint v2 http headmyshoulder github io odeint v2 odeint is a modern c library for numerically solving ordinary differential equations it is developed in a generic way using template metaprogramming which leads to extraordinary high flexibility at top performance the numerical algorithms are implemented independently of the underlying arithmetics this results in an incredible applicability of the library especially in non standard environments for example odeint supports matrix types arbitrary precision arithmetics and even can be easily run on cuda gpus several ai and deep learning libraries are being reengineered to enable the use of posits for both training and inference they will be announced as they are released license fossa status https app fossa com api projects git 2bgithub com 2fstillwater sc 2funiversal svg type large https app fossa com projects git 2bgithub com 2fstillwater sc 2funiversal ref badge large | arithmetic integer-arithmetic fixed-point-arithmetic rational-arithmetic floating-point-arithmetic posit-arithmetic interval-arithmetic quarter-precision half-precision quad-precision octa-precision arbitrary-precision arbitrary-precision-integers arbitrary-precision-arithmetic arbitrary-precision-floats c-plus-plus embedded-systems artificial-intelligence digital-signal-processing | ai |
Sia | sia logo http sia tech img svg sia green logo svg http sia tech v1 3 3 capricorn the sia project has moved to gitlab https gitlab com nebulouslabs sia | cloud blockchain decentralized distributed sia storage | blockchain |
cesium | cesium open source platform for time series inference summary cesium is an open source library that allows users to extract features from raw time series data see list http cesium ml org docs feature table html build machine learning models from these features and generate predictions for new data more information and examples http cesium ml org docs auto examples index html can be found on our home page http cesium ml org installation pip install cesium installation from source https cesium ml org docs install html license cesium is released under the 3 clause bsd licence https github com cesium ml cesium blob main license txt | ai |
|
PhpWebStudy | phpwebstudy img src https raw githubusercontent com xpf0000 phpwebstudy master build 256x256 png width 256 alt app icon php and web development environment manage tool for macos system github release https img shields io github release xpf0000 phpwebstudy svg https github com xpf0000 phpwebstudy releases total downloads https img shields io github downloads xpf0000 phpwebstudy total svg https github com xpf0000 phpwebstudy releases ko fi https ko fi com img githubbutton sm svg https ko fi com r5r2ojxtm phpwebstudy is a permanent free open source project created for php and web engineers using macos systems for development to provide a more simple and useful tool to manage the local server environment like mamp pro xampp etc some of people may not trust this program but i ll just say this as an independent developer i am committed to protecting the privacy of my users i promise that this program will not steal your privacy this program does not upload anything to anywhere it can be tested by any person or organization visit the website for detailed descriptions and tutorials on how to use it https www macphpstudy com https www macphpstudy com documentation https www macphpstudy com help 0 1 html https www phpwebstudy com https www phpwebstudy com documentation https www phpwebstudy com help 0 1 html features simple and clear graphical interface simultaneously run multiple php versions supports php5 x php8 x run as php fpm mode software version switching choose the corresponding version for development and debugging according to development needs quickly create new projects initialize with the selected framework support wordpress laravel yii2 symfony thinkphp codeigniter cakephp slim local dns server access local sites from phones and other computers using domain names customized configuration for each software instant view of log files site management set port number php version ssl certificate for each site one click setting of nginx url rewrite for common php projects one click to generate ssl self signed certificate php code obfuscation obfuscate a single file or the full project commonly used in the development of tools timestamp conversion encoding decoding port occupation of one click cleanup application interface 01 png https www macphpstudy com image index main png 02 png https www macphpstudy com image index screen3 png 03 png https www macphpstudy com image index screen4 png 04 png https www macphpstudy com image index screen5 png 05 png https www macphpstudy com image index screen6 png installation 1 github https github com xpf0000 phpwebstudy releases provides the compiled stable version of the installation package the latest version of the intel and apple m installer has been separated with arm64 for apple m without for intel pay attention not to download the wrong one 2 installation with brew brew install phpwebstudy 3 of course you can also clone the code yourself to compile and package it development cloning code bash git clone git github com xpf0000 phpwebstudy git install dependencies bash cd phpwebstudy yarn install run bash yarn run dev build bash yarn run build php versions the brew libraries do not support older php versions so if you want to use an older version of php you need to use one of brew s third party libraries example shivammathur php https github com shivammathur homebrew php phpbrew phpbrew https github com phpbrew phpbrew this application uses shivammathur php by default it will automatically add shivammathur php libraries to the brew but due to network problems it may fail to add them you can add it by yourself add command brew tap shivammathur php php extensions current one click installs include ioncube memcache memcached redis swoole xdebug ssh2 pdo sqlsrv imagick mongodb yaf sg11 for those that are not added to the one click install install them as follows and replace them with your own version of php bash cd extensions dir usr local cellar php 7 2 34 7 2 34 bin phpize configure with php config usr local cellar php 7 2 34 7 2 34 bin php config make make install technology stacks electron https electronjs org vite https vitejs dev vue3 https v3 vuejs org pinia https pinia vuejs org vue router https router vuejs org vue i18n https github com intlify vue i18n next element plus https element plus org en us xterm https xtermjs org node pty https github com microsoft node pty monaco editor https github com microsoft monaco editor contribution we welcome you to join us in this project maybe you don t need a lot of skills but a few simple things can make the project better examples of things you can do include but are not limited to testing finding bugs and filing issues translation using your own language to make software and website descriptions more accurate making product requirements and suggestions designing better looking interfaces and icons helping to share the software with a wider audience write a blog or record a video add features such as php extensions software modules common tools etc thank you to all the people who already contributed to phpwebstudy feedback and suggestions mention the issues or scan the code to add qq group qqqun png https www macphpstudy com image index qrcode0 2x png license bsd 3 clause license https github com xpf0000 phpwebstudy blob master license | php web-ide mamp mamp-pro phpstudy vue3 electron local-web-server php-obfuscator xampp development-environment php-environment local-dns-server | front_end |
aptos-blockchain-tutorial | aptos markdown aptos md aptos md 1 aptos 1 https youtu be 5ijok evv s https youtu be 5ijok evv s 2 aptos 2 https youtu be j0ptdd5xgsa https youtu be j0ptdd5xgsa 3 aptos 3 https youtu be akiwcoqt8wy https youtu be akiwcoqt8wy 4 aptos 4 docker https youtu be iikr0ldkave https youtu be iikr0ldkave 5 aptos 5 python https youtu be 9lbdlr24or4 https youtu be 9lbdlr24or4 6 aptos 6 move https youtu be lmfmzuw9zi4 https youtu be lmfmzuw9zi4 | config github-config | blockchain |
quiz-app | skillup github issues https img shields io github issues udacityfrontendscholarship quiz app svg https github com udacityfrontendscholarship quiz app issues github pull requests https img shields io github issues pr udacityfrontendscholarship quiz app svg https github com udacityfrontendscholarship quiz app pulls github forks https img shields io github forks udacityfrontendscholarship quiz app svg style social label fork https github com udacityfrontendscholarship quiz app network github stars https img shields io github stars udacityfrontendscholarship quiz app svg style social label stars https github com udacityfrontendscholarship quiz app stargazers github watchers https img shields io github watchers udacityfrontendscholarship quiz app svg style social label watch https github com udacityfrontendscholarship quiz app watchers github contributors https img shields io github contributors udacityfrontendscholarship quiz app svg https github com udacityfrontendscholarship quiz app graphs contributors logo https github com parulbindal quiz app blob master src assets images skillup 20logo jpg raw true most good programmers do programming not because they expect to get paid or get adulation by the public but because it is fun to program linus torvalds https www brainyquote com quotes linus torvalds 367382 table of contents introduction introduction technologies technologies mockups mockups data model data model er diagram er diagram collaborators collaborators moderator moderator co moderators co moderators contributing guidelines contributing guidelines thanksgiving thanksgiving introduction this application is a collaborative project made by the google udacity front end web development students during the scholarship phase technologies the technologies which will be used in developing this application are as follows react https reactjs org redux https redux js org bootstrap 4 https getbootstrap com to know more about the above mentioned technologies please refer to the project guidelines mockups signup page https github com udacityfrontendscholarship quiz app blob master src assets images sign 20up 20page jpg raw true signin page https github com udacityfrontendscholarship quiz app blob master src assets images sign 20in 20page jpg raw true dashboard page https github com udacityfrontendscholarship quiz app blob master src assets images dashboard jpg raw true dashboard page detailed https github com parulbindal quiz app blob master src assets images dashboard 20detailed png raw true challenge page https github com udacityfrontendscholarship quiz app blob master src assets images challenge 20page jpg raw true challenge page detailed https github com parulbindal quiz app blob master src assets images challenge 20page 20detailed png raw true practice page detailed https github com parulbindal quiz app blob master src assets images practice 20page 20detailed png raw true signup page detailed https github com parulbindal quiz app blob master src assets images sign 20up 20page 20detailed jpg raw true signin page detailed https github com parulbindal quiz app blob master src assets images sign 20in 20page 20detailed jpg raw true welcome page https github com parulbindal quiz app blob master src assets images welcome 20page png raw true data model view data model https www lucidchart com documents view d6d11adb 7d10 45bd a5e0 997f20a19ba4 0 helpful in understanding the workflow of redux react application demonstrates the data flow in the application er diagram view erd https www lucidchart com invitations accept 4959f428 f905 44ff 9a82 1cd55f6cf960 br this entity relationship diagram is a visual representation of the database design for the application collaborators moderator the moderator of this project is ezioda004 https github com ezioda004 co moderators the co moderators of this project are sunny puri https github com sunnypuri vanisha https github com vanisha27 kadumuri https github com kadumuri1994 parul https github com parulbindal lalitmee https github com lalitmee fayaz https github com fayazara contributing guidelines refer to this link contributing md https github com udacityfrontendscholarship quiz app blob master contributing md please make sure to read this before getting started these guidelines will help us in keeping track of who is contributing and what is being contributed to the project thanksgiving we would like to express our gratitude to the google udacity scholarship team for this idea of collaborative projects it is a huge step towards improving the learning curve special thanks to akshit udacity | front_end |
|
ECE-5725-Embedded-OS | ece 5725 design with embedded operating systems https eldorbekpulatov github io ece 5725 embedded os | os |
|
GCModeller | gcmodeller a href https gcmodeller org img src images logo png width 150 align right border 1px a gcmodeller genomics cad computer assistant design modeller system in net language doi https zenodo org badge 48901128 svg https zenodo org badge latestdoi 48901128 github all releases https img shields io github downloads smrucc gcmodeller total svg maxage 2592000 style flat square gpl licence https badges frapsoft com os gpl gpl svg v 103 https opensource org licenses gpl 3 0 build status https travis ci org smrucc gcmodeller svg branch master https travis ci org smrucc gcmodeller warning this project is a work in progress and is not recommended for production use home http gcmodeller org github https github com smrucc gcmodeller biotools https bio tools gcmodeller supported platform microsoft windows gnu linux mac microsoft azure cloud br development microsoft visualstudio 2019 visualbasic net br runtime environment scibasic https www nuget org packages scibasic v2 1 5 beta amp net framework 4 7 or mono 6 4 br installation vs2019 is required of compiles this project after the source code have been clone using git just open solution file src gcmodeller sln src gcmodeller sln and when restore nuget packages finished then you are good to go of compile gcmodeller project br note due to the reason of this project is using git submodule for manage some runtime component so that please do not directly download the project source code from github by using the donwload zip button the internal github client in the visualstudio is recommended using for download the project source code docker and database dependency part of the gcmodeller function required running linux tools through darwinism https github com xieguigang darwinism docker environment for vb net if you are running gcmodeller on windows platform this toolkit required of these environment installed on your windows server microsoft powershell sdk 3 0 latest version of docker for x64 then pull environment container image via docker pull xieguigang gcmodeller env the docker container image contains these utils that required by gcmodeller meme suite for motif analysis mothur for construct otu install database some feature in gcmodeller required the fasta sequence database was installed on a specific location on your server s filesystem please follow this instruction to install the database for gcmodeller img src http gcmodeller org dna png width 40 height 48 gcmodeller is an open source cloud computing platform for the geneticist and systems biology you can easily build a local computing server cluster for gcmodeller on the large amount biological data analysis the gcmodeller platform is original writen in visualbasic net language a feature bioinformatics analysis environment that net language hybrids programming with r language was included which its sdk is available at repository https github com smrucc r bioinformatics currently the r language hybrids programming environment just provides some bioconductor api for the analysis in gcmodeller gcmodeller is a set of utility tools working on the annotation of the whole cell system this including the whole genome regulation annotation transcriptome analysis toolkits metabolism pathway analysis toolkits and some common bioinformatics problem utils tools and common biological database i o tools is also available in gcmodeller for the net language programming directory roadmap gcmodeller gcmodeller the location of gcmodeller compile output i have config all of the project output in the path gcmodeller bin src src src gcmodeller src gcmodeller gcmodeller basic library and analysis protocols src interops src interops gcmodeller tools that dependent on the external programs src r bioconductor src r bioconductor r language hybrids environment src r sharp src r sharp the gcmodeller r language scripting engine src repository src repository gcmodeller data repository system src runtime src runtime third part library and visualbasic runtime source code tools tools data standards gcmodeller supports the sbml and biom data standards for exchanges the analysis and model data with other bioinformatics softwares supports psi data for the biological interaction network model supports obo data for ontology database like go a href http sbml org main page img src src gcmodeller models images sbml logo 70 png width 80 a a href http biom format org img src src gcmodeller models images biom format png width 80 a a href http www psidev info overview img src images data standards psi logo s png width 80 a a href http www obofoundry org img src images data standards foundrylogo png width 80 a modules amp functions gcmodeller provides a set of net libraries and cli tools for processing biological analysis data currently gcmodeller can provides these productive ready libraries 1 basically libraries ncbi data analysis toolkit genbank taxonomy nt nr database common data fasta database fastq sam data file i o class biological data standard supports sbml level 3 biom level1 psi obo biological pathway database metacyc reactome kegg data tools for net language 2 biological data visualization software api for net circos api genomic visualizing cytoscape datamodel api biological network visualizing sequencelogo molecular motif site visualize kegg pathway map visualizer 3 annotation tools a complete ncbi localblast toolkit for proteins and nucleotide sequence analysis includes parallel task library for win linux server and data analysis protocol snp toolkit nucleotide sequence topology feature site analysis toolkit regprecise database tool and meme software toolkit for the annotation of bacterial genomics regulation network go gene ontology annotation tools kegg go gsea functional enrichment tools and reference genome background model creator based on uniprot database 4 r language hybrids environment for bioinformatics includes basically r language api wrapper for visualbasic like api in base utils stats namespace from r base and some r package wrapper api from cran and bioconductor is also included gcmodeller r language scripting 5 webapi wrapper for kegg database and regprecise database 6 feature tools cellular module simulator and virtual cell model generator protocol proteomics data analysis toolkit single cell data analysis toolkit gcmodeller r scripting here is a code snapshot of r scripting for drawing sequence logo input data is accepted from the commandline input r demo script for create sequence logo based on the msa alignment analysis nt base frequency is created based on the msa alignment operation imports bioseq sequencelogo from seqtoolkit dll imports bioseq fasta from seqtoolkit dll script cli usage r sequencelogo r seq input fasta title logo title save output png get input data from commandline arguments and fix for the optional arguments default value by apply or default syntax for non logical values let seq fasta as string seq stop no sequence input data for draw sequence logo let logo png as string save seq fasta logo png let title as string title basename seq fasta read sequence and then do msa alignment finally count the nucleotide base frequency and then draw the sequence logo by invoke sequence logo drawer api seq fasta read fasta msa of plot seqlogo title save graphics file logo png run the r script from commandline cmd echo off r sequencelogo r seq lexa fasta save lexa png title lexa images lexa png publications here listing the scientific paperworks that based on the analysis services of gcmodeller niu x n et al 2015 complete sequence and detailed analysis of the first indigenous plasmid from xanthomonas oryzae pv oryzicola bmc microbiol 15 1 1 15 doi 10 1186 s12866 015 0562 x bacterial plasmids have a major impact on metabolic function and adaptation of their hosts an indigenous plasmid was identified in a chinese isolate gx01 of the invasive phytopathogen xanthomonas oryzae pv oryzicola xoc the causal agent of rice bacterial leaf streak bls to elucidate the biological functions of the plasmid we have sequenced and comprehensively annotated the plasmid 2016 05 17 png gallery src gcmodeller analysis singlecell stdeconvolve demo raw pixels png single cell data toolkit includes in gcmodeller phenograph src gcmodeller analysis singlecell phenograph phenograph stdeconvolve src gcmodeller analysis singlecell stdeconvolve stdeconvolve images cmeans keggset png images upsetplot png src workbench r 23 demo hts patterns png src workbench r 23 demo hts expression patterns r images vocano plot png images kegg pathway network clusters png images rsd p density png images clusters scatter png images xcb tcs uniprot taxonomy 314565 go enrichment converts go enrichment pvalue 0 05 png img src images biological process png width 285 img src images cellular component png width 285 img src images molecular function png width 285 img src manual kegg unigenes blast m8 filter ko catalogs kegg level a png width 435 img src images go enrichment png width 435 images fur lightbox png images xanthomonas oryzae oryzicola bls256 uid16740 lightbox png images pxocgx01 lightbox png images phenotypic btree lightbox png images pxocgx01 blastx lightbox png visit our project home http gcmodeller org for developers here are some released library of the gcmodeller is published on nuget then you can install these library in visualstudio from package manager console bash install microsoft visualbasic scibasic runtime via nuget https github com xieguigang scibasic pm install package scibasic pre the gcmodeller core base library was released https github com smrucc gcmodeller core pm install package gcmodeller core the ncbi localblast analysis toolkit https github com smrucc ncbi localblast pm install package ncbi localblast for user the gcmodeller demo script and data for user tutorials can be download from these public data repository xanthomonas campestris pv campestris 8004 gcmodeller genomics modelling project https github com smrucc xanthomonas campestris 8004 uid15 genome map plot of xanthomonas campestris pv campestris 8004 https raw githubusercontent com smrucc xanthomonas campestris 8004 uid15 master thumbnails map part a png https github com smrucc xanthomonas campestris 8004 uid15 tree master genome chromsome map https raw githubusercontent com smrucc xanthomonas campestris 8004 uid15 master thumbnails map part b png https github com smrucc xanthomonas campestris 8004 uid15 tree master genome chromsome map img src images links osi certified png width 40px images links github ico copyleft copy smrucc genomics http smrucc org 2016 all rights reversed | gcmodeller biological-data-analysis scibasic microsoft-visualbasic dotnet genomics genome-annotation r-language bioinformatics single-cell | os |
Smart-Clock | smart clock author br zxc41329 at gmail com br 106522054 at cc ncu edu tw date 2018 06 22 environment nucleo f767zi http www st com en evaluation tools nucleo f767zi html nodemcu http nodemcu com index cn html ide keil uvision5 http www2 keil com mdk5 uvision arduino ide https www arduino cc en main software report smart clock report report pdf system design smart clock design https i imgur com 3earcna png demo smart clock https i imgur com eeqv5jo png https youtu be xv4xlsmcjhs | os |
|
Embedded-System-Design-S22 | embedded system design s22 welcome to the repository for my assignments in the subject embedded system design this course instructed by professor mcclure from the department of electrical computer and energy engineering delves into the fundamentals of hardware and firmware design for embedded systems throughout this course i have acquired a diverse set of skills and knowledge which include skills and knowledge processor selection understanding the criteria and considerations for selecting an appropriate processor for embedded system development power delivery and decoupling knowledge of power delivery techniques and decoupling methods to ensure reliable operation of embedded systems clocks and resets familiarity with clocking and resetting mechanisms and their role in system synchronization and initialization assembly programming proficiency in low level assembly programming for embedded systems embedded c programming competence in programming embedded systems using the c programming language incremental development hw sw experience in iterative hardware and software development processes for embedded systems test equipment and instrumentation utilizing various test equipment and instrumentation such as oscilloscopes multimeters and logic analyzers for debugging and validation debugging techniques understanding and applying effective debugging techniques for identifying and resolving software and hardware issues data sheets ability to interpret and utilize data sheets provided by microcontroller manufacturers for hardware understanding and programming requirements bus cycles transaction types timing diagrams understanding communication protocols timing requirements and transaction types through bus cycles and timing diagrams memory maps and chip select logic managing memory and controlling external devices through memory mapping and chip select logic serial interfaces rs 232 i2c spi implementing popular serial communication interfaces in embedded systems i o port pin driver circuits knowledge of i o port pin driver circuits including pull up pull down resistors and open drain configurations in circuit programming ability to program microcontrollers without removing them from the circuit using in circuit programming techniques device drivers developing device drivers for interfacing with various peripherals and external devices interrupts and isr s understanding interrupts and writing interrupt service routines isr s for time critical events in embedded systems memory mapped i o implementing memory mapped i o for accessing and controlling peripheral devices data conversion dac s adc s understanding and utilizing digital to analog converters dac s and analog to digital converters adc s in embedded systems passive components knowledge of passive components such as resistors capacitors and inductors and their applications in embedded system design design reviews and trade offs conducting design reviews and making trade offs to meet system requirements and constraints entrepreneurship understanding the entrepreneurial aspects of embedded system design including product development and commercialization considerations assignments this repository contains a collection of assignments that demonstrate my understanding and application of the concepts covered in the course each assignment is accompanied by detailed descriptions source code and relevant documentation feel free to explore the individual assignment folders for more information final project as a culmination of the course i have completed a significant final project this project extends the base microcontroller board developed earlier in the course and showcases my comprehensive knowledge and skills acquired throughout the semester detailed documentation and source code for the final project can be found in the corresponding folder contact if you have any questions or would like to discuss any aspect of this repository please feel free to contact me at kijo7257 colorado edu thank you kiran jojare | os |
|
AI-Airlift | image classification with deep learning hello and welcome to this lab on computer vision in this lab you ll explore some tools and techniques for creating and deploying deep learning predictive models for image classification note to complete this lab you will need a microsoft azure subscription if you don t already have one sign up for a free trial at https azure microsoft com en us free exercises exercise 1 exploring images exercise1 md exercise 2 training an image classifier exercise2 md exercise 3 deploying a classification model exercise3 md exercise 4 if time permits transfer learning exercise4 md | ai |
|
CS501_HW7 | cs501 hw7 cs 501 mobile app development fragment transactions implicit intents menus animations w7 p1 what s wrong with this code exploring fragment transactions and how they interact with each other w7 p2 maintaining state bundles and sharedpreferences a very simple app with one button one imageview and one edittext clicking on the button will load a random image into the imageview this app allows us to practice sharedpreferences when it comes to ondestroy and oncreate to remember the state of the app w7 p3 spring break chooser this app works with intents with return values google maps and an accelerometer the app allows the user to select a language from a listview and speak into the device with a speech to text intent upon shaking the phone using an accelerometer a geo uri intent will open up a maps app and display a spring break location based on the language selected simultaneously the spring break chooser app will say hello in the respective language w7 p4 animations an app that has two xml based animations 1 a 10 second animation that results in a centered view object fading to 50 for the first 5 seconds rotate counter clockwise 2 times in total and pivot from the center for seconds 1 3 and slide down then back to center for the remainder of the animation 2 an 8 second animation that results in a view object growing from the center up to double in size for seconds 0 2 rotate 3 times in total and pivot in the bottom left corner for seconds 1 4 bounce for seconds 4 5 slide down then back to the center for seconds 5 6 slide left then back to the center for seconds 6 7 then slide up and then back to the center while reverting back to the original size and pivoting from the center for seconds 7 8 | front_end |
|
lincoln_exercise_with_airflow_and_gcp | lincoln exercise with airflow and gcp exercise given by a consultant company to test my data engineering skills including cloud storage and airflow features prerequisites to execute this airflow dag install airflow and launch it with docker create a gcp service account key with the name gcp account service key json create a gcp cloud storage named servier test technique with the datasources inside it datasource pubmed csv datasource pubmed json datasource clinical trials csv datasource drugs csv install the pyton librairies pip install r requirements | cloud |
|
Natural-Language-Processing-Coursera | natural language processing coursera natural language processing coursera mooc | ai |
|
rforrecovery | rforrecovery information technology | server |
|
astro-design-system | title introduction description docs intro layout layouts mainlayout astro astro design system theme astro design system is the easiest way to start your our design system since astro is compatible with many frameworks you can import your components and document them right in the markdown files getting started adding new sections although it s not required you can create folders for new sections to show the section on the left side navigation add it to the navigation config file at src config ts example js export const sidebar text core header true text introduction link core introduction text components header true text buttons link components buttons text new section header true text new component link new section new component md adding new pages to add new pages just create an astro or markdown file in src pages section my page md remember to add it to the navigation config in src config ts so it shows up in the left side navigation you re free to organize the pages however you want customizing core section colors typography shadows if you want to customize the default colors typography or shadows you can find the configuration file at src config design config ts feel free to add new pages to the core section customizing the page layout you can find the css for the pages in src styles content scss adding your components astro is great for design systems because it allows you to import components from different frameworks like react vue or svelte to get started check how the mainbutton component is used in the src pages en buttons md file you can import your component library or create your own and document it easily component preview utility there s a class called component preview that you can use to wrap your component in a grid and it will look like this div class component preview button class text white bg blue 500 px 4 py 2 rounded md your component button div have fun astro design system template was made by jordienr https twitter com jordienr for personal and commercial use | astro design-system theme | os |
toxic_comments_classifier | hi guys welcome to the toxic comments classifier repo before you start the tutorial please do the following for a smooth less buggy experience 1 clone the repo to your local directory 2 create a new environment through anaconda prompt enter conda env create f toxic test yml enter python m ipykernel install user name toxic display name toxic enter conda activate toxic you can deactivate the env later 3 download visual studio code if you do not have it to open the py and html files required for flask how to run the flask app 1 open anaconda prompt 2 change directory to flask app for toxic comments cd 3 enter python toxic app py to run the python file 4 if you encounter a module not found error enter pip install flask 5 copy the ip address where the flask is running at eg http 127 0 0 1 5000 into your browser 6 you should see the app in action hope you find the tutorials useful if you have any constructive feedback please send an email to linebyline ai gmail com thank you | ai |
|
CITMA | citma collaborative information technology application | server |
|
dataset-tools | various dataset tools installation requirements opencv pcl and flann for evaluate reconstruction sudo apt get install libpcl dev libflann dev glm for trajectory tool sudo apt get install libglm dev sudo apt get install gtk2 engines pixbuf gnome themes standard example git clone git github com martinruenz dataset tools git cd dataset tools mkdir release cd release cmake make j8 optionally add to path assumed in some steps below log out and in again afterwards echo path path pwd profile howtos how to evaluate your object aware slam method completely automatically analyse segmentation and trajectory quality the script automatisation cofusion jl was written for this purpose and evaluates the object segmentation and trajectory quality of your method it assumes that you have the following data available ground truth segmentation exported segmentation ground truth trajectories file name has to contain corresponding label id exported trajectories br example using co fusion cofusion basedir path to carscene4 dir colour depthdir depth cal calibration txt exportdir path to export segminnew 0 008 crfsmooth 1 crfpos 0 51 es ep run q keep cofusion jl gt poses path to carscene4 trajectories ex poses path to export gt masks path to carscene4 masks id ex masks path to export out path to output the script automatically tries to perform the steps of the following howto by converting the trajectories using the frame with the best intersection over union score as a result you will get an intersection over union graph see the following image as well as a trajectory plot as in the image of the next howto visualisation images iou example svg how to compare an object trajectory of your non static slam method with ground truth data since your slam method is not aware of the ground truth coordinate system the origin of the given object your system has to pick a random origin an alignment method has to be used before a meaningful evaluation is possible luckily your system should already align moving objects to the camera so if you pick a frame which aligns camera and object nicely it can be used to compute the ground truth object origin in the reference frame of your object subsequently your and the ground truth origin coincide and evaluation algorithms can be applied this is how it is done export the object poses produced by your system in this format t frame t x y z qx qy qz qw export the ground truth poses from blender see io export pose py run convert poses to map the obejct origin like convert poses frame good frame number object your poses txt camera your camera poses txt gtobject gt poses txt gtcamera gt cam poses txt out mapped origin txt run an evaluation script such as evaluate ate py by tum wget https svncvpr in tum de cvpr ros pkg trunk rgbd benchmark rgbd benchmark tools src rgbd benchmark tools evaluate ate py wget https svncvpr in tum de cvpr ros pkg trunk rgbd benchmark rgbd benchmark tools src rgbd benchmark tools associate py python evaluate ate py verbose plot your plot pdf your poses txt mapped origin txt the result should look something like this visualisation images ate example svg how to create a slam dataset using blender todo example blender file export depth export segmentation reference to export poses calibration convert depth convert depth described below convert depth dir depth original outdir depth converted cx 320 cy 240 fx 360 fy 480 z also if convert colour masks to id masks cp r maskdir id masks label finder dir id masks outdir id masks prefix mask width 4 starti 1 c 255 0 0 r 1 1 1 repeat calling label finder for different colours c and different ids r where the parameter is id id id tools scripts blender io export pose py blender addon script that enables the export of object and camera poses the exported format is either t x y z qx qy qz qw or t x y z rx ry rz screenrecording images io export pose nops gif get calibration py script to export intrinsic pinhole camera parameters from blender written by the user rfabbri of http blender stackexchange com http blender stackexchange com questions 15102 what is blenders camera projection matrix model 38189 trajectoryviewer jl simple julia script that visualises a list of trajectories in the format t x y z qx qy qz qw screenrecording images trajectoryviewer gif c tools convert depth blender when extracting depth maps from blender the depth values are usually not projective and hence have to be converted to be used common scenarios this tool can perform the necessary conversion it is also able to add noise to depth values input depth map s exr files optional parameters output depth map s exr files visualisation images convert depth svg convert exrtorgb convert exr to rgb image file usually for visualisation the floating point input is mapped from min max to 0 255 convert klgtoply allows you to extract colour images depth images and ply point clouds from each each frame of a klg file convert masks convert colour mask images cv 8uc3 to id mask images cv 8uc1 the tool ensures that the re mapping is consistent throughout a dataset convert poses convert the ground truth origin of an object to world coordinate poses in your export for each frame see howtos klgviewer view a klg file depth rgb like a video label associator assume you have two subsequent frames with object labels but incoherent label colors this tool tries to correctly associate labels in order to make them coherent label finder highlight a color in a dataset like camvid also allows you to replace that colour screenrecording images find label gif label merger merge labels with certain amount of neighbours | ai |
|
Autostitch | autostitch introduction in this project we will implement a system to combine a series of horizontally overlapping photographs into a single panoramic image we are given the orb feature detector and descriptor we will use orb to first detect discriminating features in the images and find the best matching features in the other images then using ransac we will automatically align the photographs determine their overlap and relative positions and then blend the resulting images into a single seamless panorama click here http www cs cornell edu courses cs5670 2018sp projects pa3 index html to view projects introduction features using ransac to automatically align the photographs determine their overlap and relative positions and then blend the resulting images into a single seamless panorama with previous features detection and matching knowledge we find the matched images and create program that can calculate homography approach transformation parameters and transfrom them so that we align images from different angels in a consistent platform create panoramas with spherical warp mappings method in compute homography we use svd singular value decomposition method normalize the image with the accumulated weight channel we deal with diffrent images edges when creating panorama with edge feather method we can create 360 degree panorama structure name function resources available images to create panorama src warp py warp each image into spherical coordinates src alignment py compute the alignment of image pairs src blend py stitch and crop the resulting aligned images src test py test whether function in features py is same with task s command src gui py an gui for users to create panorama usages requirements linux windows macos python 2 7 python 3 5 cv2 numpy pandas scipy compilation python cd python test py cd python gui py examples input images https github com reynoldzhao project3 autostitch raw master resources yosemite panorama yosemite1 jpg https github com reynoldzhao project3 autostitch raw master resources yosemite panorama yosemite3 jpg https github com reynoldzhao project3 autostitch raw master resources yosemite panorama yosemite4 jpg https github com reynoldzhao project3 autostitch raw master resources yosemite panorama yosemite2 jpg panorama https github com reynoldzhao project3 autostitch raw master project3 results yosemite pano homography blendwidth50 png https github com reynoldzhao project3 autostitch raw master project3 results yosemite pano translation blendwidth50 png | ai |
|
kafka-connect-iot-mqtt-connector-example | apache kafka kafka connect mqtt connector sensor data this demo shows an internet of things iot integration example using apache kafka kafka connect mqtt connector sensor data this project does not include any source code as kafka connect allows integration with data sources and sinks just with configuration example configuration and step by step guide can be found below if you want to find more details about kafka mqtt integration take a look at my slides from kafka summit 2018 in san francisco iot integration with mqtt and apache kafka https www slideshare net kaiwaehner iot integration with mqtt and apache kafka the video recording is available on the website of kafka summit for free kafka mqtt integration video recording https www confluent io kafka summit sf18 processing iot data from end to end architecture sensor data via mqtt broker and kafka connect mqtt connector to kafka cluster this project focuses on the integration of mqtt sensor data into kafka via mqtt broker and kafka connect for further processing pictures apache kafka connect mqtt broker mosquitto integration png as alternative to using kafka connect you can also leverage confluent mqtt proxy to integrate iot data from iot devices directly withou the need for a mqtt broker see deep learning udf for ksql for streaming anomaly detection of mqtt iot sensor data https github com kaiwaehner ksql udf deep learning mqtt iot for an example and source code if you want to see the other part integration with sink applications like elasticsearch grafana please take a look at the project ksql for streaming iot data https github com kaiwaehner ksql fork with deep learning function which shows how to realize the integration with elasticsearch via kafka connect live demo video mqtt with kafka connect and mqtt proxy if you want to see apache kafka mqtt integration in a video please check out the following 15min recording showing a demo my two github examples apache kafka mqtt integration pictures mqtt apache kafka integration confluent proxy connect png https www youtube com watch v l38 6ilgeke kafka connect configuration no source code needed here is the full configuration for the mqtt connector for kafka connect s standalone mode which we use with confluent cli for a local setup name mqttsourceconnector1 connector class io confluent connect mqtt mqttsourceconnector tasks max 1 mqtt server uri required configuration mqtt topics required configuration for distributed mode you can use the same configuration with rest api curl s x post h content type application json http localhost 8083 connectors d name required configuration config connector class io confluent connect mqtt mqttsourceconnector tasks max 1 mqtt server uri required configuration mqtt topics required configuration kafka topics required configuration the documentation explains the differences between standalone and distributed kafka connect mode https docs confluent io current connect concepts html connect concepts in short standalone mode is the simplest mode where a single process is responsible for executing all connectors and tasks distributed mode is used in most production scenarios and provides scalability and automatic fault tolerance for kafka connect you can also use distributed mode for local development leveraging its advantages like a rest api even if you just have one single connect instance and you can scale it later easily without complex changes we will use distributed mode in this project therefore confluent documentation contains more details about installing and using confluent s mqtt connector https docs confluent io current connect kafka connect mqtt how to run it requirements java 8 confluent platform 5 0 https www confluent io download confluent enterprise if you want to use the confluent mqtt proxy confluent open source if you just want to run the ksql udf and send data via kafkacat instead of mqtt mqtt client and broker this demo uses mosquitto https mosquitto org download confluent mqtt connector https www confluent io connector kafka connect mqtt a kafka connect based connector to send and receive mqtt messages very easy installation via confluent hub just one command confluent hub install confluentinc kafka connect mqtt 1 2 3 optional mqtt fx https mqttfx jensd de a nice simple ui to test mqtt pub sub not required just makes life more comfortable the code is developed and tested on mac and linux operating systems as kafka does not support and work well on windows this is not tested at all step by step demo follow these steps to configure the mqtt connector start all components generate mqtt sensor data and consume it from a kafka consumer https github com kaiwaehner kafka connect iot mqtt connector example blob master live demo kafka connect iot mqtt connector adoc | kafka kafka-connect kafka-connector mqtt mqtt-broker mqtt-connector opensource confluent confluent-kafka confluent-platform iot internet-of-things mosquitto | server |
beginning-app-development-with-flutter | apress source code this repository accompanies beginning app development with flutter create cross platform mobile apps https www apress com 9781484251805 by rap payne apress 2020 comment cover cover image 9781484251805 jpg download the files as a zip using the green button or clone the repository to your machine using git releases release v1 0 corresponds to the code in the published book without corrections or updates contributions see the file contributing md for more information on how you can contribute to this repository | front_end |
|
ota-for-aws-iot-embedded-sdk | aws iot over the air update library api documentation pages for current and previous releases of this library can be found here https aws github io ota for aws iot embedded sdk the ota library enables you to manage the notification of a newly available update download the update and perform cryptographic verification of the firmware update using the library you can logically separate firmware updates from the application running on your devices the ota library can share a network connection with the application saving memory in resource constrained devices in addition the ota library lets you define application specific logic for testing committing or rolling back a firmware update the library supports different application protocols like message queuing telemetry transport mqtt and hypertext transfer protocol http and provides various configuration options you can fine tune depending on network type and conditions this library is distributed under the mit open source license license this library has gone through code quality checks including verification that no function has a gnu complexity https www gnu org software complexity manual complexity html score over 10 this library has also undergone static code analysis from coverity static analysis https scan coverity com see memory requirements for this library here docs doxygen include size table md aws iot over the air update library v3 4 0 source code https github com aws ota for aws iot embedded sdk tree v3 4 0 source is part of the freertos 202210 00 lts https github com freertos freertos lts tree 202210 00 lts release aws iot over the air update library v3 3 0 source code https github com aws ota for aws iot embedded sdk tree v3 3 0 source is part of the freertos 202012 01 lts https github com freertos freertos lts tree 202012 01 lts release upcoming changes intended for release in q4 2023 a major version update of this library will make it compliant with the freertos core branded libraries design goal of being free of any dependencies other than the c library the monolithic design of the existing ota library doesn t make it easy to make use case specific modifications such as changing the ota update source the new major version will refactor the library amongst other things to increase modularity and simplify the use of any firmware source or communication mechanism both supported by aws and not while the old version of this library will remain available we will not be developing it further and will instead focus on the newer major versions going forward to see our current progress towards this goal please see freertos labs project ota example for aws iot core https github com freertos labs project ota example for aws iot core aws iot over the air updates config file the aws iot over the air updates library exposes configuration macros that are required for building the library a list of all the configurations and their default values are defined in ota config defaults h source include ota config defaults h to provide custom values for the configuration macros a custom config file named ota config h can be provided by the user application to the library by default a ota config h custom config is required to build the library to disable this requirement and build the library with default configuration values provide ota do not use custom config as a compile time preprocessor macro building the library the otafilepaths cmake otafilepaths cmake file contains the information of all source files and the header include paths required to build the aws iot over the air updates library as mentioned in the previous section either a custom config file i e ota config h or the ota do not use custom config macro needs to be provided to build the aws iot over the air updates library for a cmake example of building the aws iot over the air updates library with the otafilepaths cmake file refer to the coverity analysis library target in the test cmakelists txt test cmakelists txt file building unit tests checkout cmock submodule by default the submodules in this repository are configured with update none in gitmodules gitmodules to avoid increasing clone time and disk space usage of other repositories like aws iot device sdk for embedded c https github com aws aws iot device sdk embedded c that submodules this repository to build unit tests the submodule dependency of cmock is required use the following command to clone the submodule git submodule update checkout init recursive test unit test cmock source dependency corejson platform prerequisites for building the library cmake 3 13 0 or later and a c90 compiler for running unit tests ruby 2 0 0 or later is additionally required for the cmock test framework that we use for running the coverage target gcov and lcov are additionally required steps to build unit tests 1 go to the root directory of this repository make sure that the cmock submodule is cloned as described above checkout cmock submodule 1 run the cmake command cmake s test b build 1 run this command to build the library and unit tests make c build all 1 the generated test executables will be present in build bin tests folder 1 run cd build ctest to execute all tests and view the test run summary migration guide how to migrate from v2 0 0 release candidate to v3 4 0 the following table lists equivalent api function signatures in v2 0 0 release candidate and v3 4 0 declared in ota h source include ota h v2 0 0 release candidate v3 4 0 notes otastate t ota shutdown uint32 t tickstowait otastate t ota shutdown uint32 t tickstowait uint8 t unsubscribeflag unsubscribeflag indicates if unsubscribe operations should be performed from the job topics when shutdown is called set this as 1 to unsubscribe 0 otherwise how to migrate from version 1 0 0 to version 3 4 0 for ota applications refer to ota migration document https docs aws amazon com freertos latest portingguide porting migration ota html for the summary of updates to the api migration document for ota pal https docs aws amazon com freertos latest portingguide porting migration ota pal html also provides a summary of updates required for upgrading the ota pal to work with v3 4 0 of the library porting in order to support aws iot over the air updates on your device it is necessary to provide the following components 1 port for the ota portable abstraction layer pal https docs aws amazon com embedded csdk 202103 00 lib ref libraries aws ota for aws iot embedded sdk docs doxygen output html ota porting html ota porting pal 1 os interface https docs aws amazon com embedded csdk 202103 00 lib ref libraries aws ota for aws iot embedded sdk docs doxygen output html ota porting html ota porting os 1 mqtt interface https docs aws amazon com embedded csdk 202103 00 lib ref libraries aws ota for aws iot embedded sdk docs doxygen output html ota porting html ota porting mqtt for enabling data transfer over http dataplane the following component should also be provided 1 http interface https docs aws amazon com embedded csdk 202103 00 lib ref libraries aws ota for aws iot embedded sdk docs doxygen output html ota porting html ota porting http note when using ota over http dataplane mqtt is required for control plane operations and should also be provided cbmc to learn more about cbmc and proofs specifically review the training material here https model checking github io cbmc training the test cbmc proofs directory contains cbmc proofs in order to run these proofs you will need to install cbmc and other tools by following the instructions here https model checking github io cbmc training installation html cbmc locally to run a single cbmc proof locally you can build the makefile in any of the cbmc proofs the makefile is located in the test cbmc proof the proof you want directory running make will produce a html based report nearly identical to the one produced by the ci step a couple notes about cbmc proofs macos doesn t implement posix message queues mqueue h it is possible that macos fails to recognize your loop unwinding identifiers for function from the c standard libraries for this case you ll want to use the builtin function chk identifier e g instead of using memcpy add builtin memcpy chk for example the requestjob mqtt proof fails on macos with the following error loop unwinding failures trace builtin strncpy chk unwind 0 in line 36 in file builtin library builtin strncpy chk to solve this issue replace strncpy with builtin strncpy ch on this line https github com aws ota for aws iot embedded sdk blob main test cbmc proofs requestjob mqtt makefile l16 reference examples please refer to the demos of the aws iot over the air updates library in the following location for reference examples on posix and freertos platform location posix aws iot device sdk for embedded c https github com aws aws iot device sdk embedded c tree main demos ota freertos freertos freertos https github com freertos freertos tree main freertos plus demo aws ota windows simulator freertos freertos aws reference integrations https github com aws amazon freertos tree main demos ota documentation existing documentation for pre generated documentation please see the documentation linked in the locations below location aws iot device sdk for embedded c https github com aws aws iot device sdk embedded c releases and documentation freertos org https freertos org documentation api ref ota for aws iot embedded sdk docs doxygen output html index html note that the latest included version of coremqtt may differ across repositories generating documentation the doxygen references were created using doxygen version 1 9 2 to generate the doxygen pages please run the following command from the root of this repository shell doxygen docs doxygen config doxyfile contributing see contributing md github contributing md for information on contributing | server |
|
NewProject_1 | newproject 1 information systems and technologies 3 | server |
|
MLBox | mlbox machine learning algorithms implementations blogs decision tree http pytlab github io 2017 07 09 e6 9c ba e5 99 a8 e5 ad a6 e4 b9 a0 e7 ae 97 e6 b3 95 e5 ae 9e e8 b7 b5 e5 86 b3 e7 ad 96 e6 a0 91 naive bayes http pytlab github io 2017 07 11 e6 9c ba e5 99 a8 e5 ad a6 e4 b9 a0 e5 ae 9e e8 b7 b5 e6 9c b4 e7 b4 a0 e8 b4 9d e5 8f b6 e6 96 af naive bayes logistic http pytlab github io 2017 07 13 e6 9c ba e5 99 a8 e5 ad a6 e4 b9 a0 e7 ae 97 e6 b3 95 e5 ae 9e e8 b7 b5 logistic e5 9b 9e e5 bd 92 e4 b8 8e e6 a2 af e5 ba a6 e4 b8 8a e5 8d 87 e7 ae 97 e6 b3 95 e4 b8 8a logistic http pytlab github io 2017 07 15 e6 9c ba e5 99 a8 e5 ad a6 e4 b9 a0 e7 ae 97 e6 b3 95 e5 ae 9e e8 b7 b5 logistic e5 9b 9e e5 bd 92 e4 b8 8e e6 a2 af e5 ba a6 e4 b8 8a e5 8d 87 e7 ae 97 e6 b3 95 e4 b8 8b svm http pytlab github io 2017 08 15 e6 9c ba e5 99 a8 e5 ad a6 e4 b9 a0 e7 ae 97 e6 b3 95 e5 ae 9e e8 b7 b5 e6 94 af e6 8c 81 e5 90 91 e9 87 8f e6 9c ba svm e7 ae 97 e6 b3 95 e5 8e 9f e7 90 86 svm http pytlab github io 2017 08 30 e6 9c ba e5 99 a8 e5 ad a6 e4 b9 a0 e7 ae 97 e6 b3 95 e5 ae 9e e8 b7 b5 svm e6 a0 b8 e5 87 bd e6 95 b0 e5 92 8c e8 bd af e9 97 b4 e9 9a 94 svm smo http pytlab github io 2017 09 01 e6 9c ba e5 99 a8 e5 ad a6 e4 b9 a0 e7 ae 97 e6 b3 95 e5 ae 9e e8 b7 b5 svm e4 b8 ad e7 9a 84smo e7 ae 97 e6 b3 95 platt smo svm http pytlab github io 2017 10 15 e6 9c ba e5 99 a8 e5 ad a6 e4 b9 a0 e7 ae 97 e6 b3 95 e5 ae 9e e8 b7 b5 platt smo e5 92 8c e9 81 97 e4 bc a0 e7 ae 97 e6 b3 95 e4 bc 98 e5 8c 96svm http pytlab github io 2017 10 24 e6 9c ba e5 99 a8 e5 ad a6 e4 b9 a0 e7 ae 97 e6 b3 95 e5 ae 9e e8 b7 b5 e6 a0 87 e5 87 86 e4 b8 8e e5 b1 80 e9 83 a8 e5 8a a0 e6 9d 83 e7 ba bf e6 80 a7 e5 9b 9e e5 bd 92 lasso http pytlab github io 2017 10 27 e6 9c ba e5 99 a8 e5 ad a6 e4 b9 a0 e5 ae 9e e8 b7 b5 e5 b2 ad e5 9b 9e e5 bd 92 e5 92 8classo e5 9b 9e e5 bd 92 http pytlab github io 2017 11 03 e6 9c ba e5 99 a8 e5 ad a6 e4 b9 a0 e7 ae 97 e6 b3 95 e5 ae 9e e8 b7 b5 e6 a0 91 e5 9b 9e e5 bd 92 | ai |
|
MERN-Stack-Web-Development-with-Ultimate-Authentication | mern stack web development with ultimate authentication mern stack web development with ultimate authentication by packt publishing | front_end |
|
boring-wozniak | welcome to project boring wozniak table of contents 1 table of contents table of contents 2 introduction introduction 3 authors authors 4 the case study the case study 5 the data the data 5 why is wozniak boring why is wozniak boring introduction this repository is the authors implementation for the projects developed during the database 2 https en didattica unipd it off 2021 lm in in2547 004pd inq0091645 n0 course taught at the department of information engineering https www unipd it en dei at the university of padova https www unipd it en the goal of the projects is to boost soft skills like teamwork and collaboration project deadlines are aligned with the schedule and contents of the lectures so that students can immediately apply the learned concepts to a case study of their own interests authors aliia sultanova mailto aliia sultanova studenti unipd it michele canale mailto michele canale 1 studenti unipd it odai mohammad mailto odai mohammad studenti unipd it yongxiang ji mailto yongxiang ji studenti unipd it the case study the authors case study is modeling the transportation network in italy the data used is obtained from openstreetmap this data can be obtained from geofabrik s free download server https download geofabrik de index html the data the modeled data can be obtained from geofabrik s free download server https download geofabrik de index html more specifically the data for italy s transportation network can be downloaded from this link https download geofabrik de europe italy latest osm pbf why is wozniak boring when a container is created using docker docker provides a way to name the container using the name container name flag however if no name is provided by the user while creating running a docker container docker automatically assigns the container a name digging into the source code of docker on github we come across the algorithm used to generate the names the code is written in the file names generator test go https github com docker docker ce blob master components engine pkg namesgenerator names generator go at line 841 we have a function getrandomname that generates the name of the docker container func getrandomname retry int string begin name left rand intn len left right rand intn len right nolint gosec g404 use of weak random number generator math rand instead of crypto rand if name boring wozniak steve wozniak is not boring goto begin if retry 0 name strconv itoa rand intn 10 nolint gosec g404 use of weak random number generator math rand instead of crypto rand return name looking at this snippet of the function if name boring wozniak steve wozniak is not boring goto begin our friends at docker think that steve wozniak is not boring we agree but we couldn t resist throwing an inside joke into our project | server |
|
E-commerce_Website | e commerce website i have developed this e commerce website during my software engineering course using php and connected the database through the xampp server | server |
|
drone-stm32-map | crates io https img shields io crates v drone stm32 map svg https crates io crates drone stm32 map maintenance https img shields io badge maintenance actively developed brightgreen svg drone stm32 map cargo rdme start stm32 peripheral mappings for drone an embedded operating system this crate uses cmsis svd https arm software github io cmsis 5 svd html index html files provided by stmicroelectronics https www st com to automatically generate drone register and interrupt bindings however only the corresponding reference manual is the single source of truth a difference between this crate bindings and the reference manual is considered a bug fixing such a bug is not a breaking change this crate re exports the contents of drone cortexm map module and is a drop in replacement for it supported devices drone stm32 map core name reference manual available features stm32f100 arm cortex m3 r1p1 rm0041 https www st com resource en reference manual cd00246267 pdf dma gpio spi tim stm32f101 arm cortex m3 r1p1 rm0008 https www st com resource en reference manual cd00171190 pdf dma gpio spi tim stm32f102 arm cortex m3 r1p1 rm0008 https www st com resource en reference manual cd00171190 pdf dma gpio spi tim stm32f103 arm cortex m3 r1p1 rm0008 https www st com resource en reference manual cd00171190 pdf dma gpio spi tim stm32f107 arm cortex m3 r1p1 rm0008 https www st com resource en reference manual cd00171190 pdf dma gpio spi tim stm32f303 arm cortex m4f r0p1 rm0316 https www st com resource en reference manual dm00043574 pdf adc dma exti gpio i2c tim stm32f401 arm cortex m4f r0p1 rm0368 https www st com resource en reference manual dm00096844 pdf adc dma exti gpio i2c spi tim uart stm32f405 arm cortex m4f r0p1 rm0090 https www st com resource en reference manual dm00031020 pdf adc dma exti gpio i2c spi tim uart stm32f407 arm cortex m4f r0p1 rm0090 https www st com resource en reference manual dm00031020 pdf adc dma exti gpio i2c spi tim uart stm32f410 arm cortex m4f r0p1 rm0401 https www st com resource en reference manual dm00180366 pdf adc dma exti gpio i2c spi tim uart stm32f411 arm cortex m4f r0p1 rm0383 https www st com resource en reference manual dm00119316 pdf adc dma exti gpio i2c spi tim uart stm32f412 arm cortex m4f r0p1 rm0402 https www st com resource en reference manual dm00180369 pdf adc dma exti gpio i2c spi tim uart stm32f413 arm cortex m4f r0p1 rm0430 https www st com resource en reference manual dm00305666 pdf adc dma exti gpio i2c spi tim uart stm32f427 arm cortex m4f r0p1 rm0090 https www st com resource en reference manual dm00031020 pdf adc dma exti gpio i2c spi tim uart stm32f429 arm cortex m4f r0p1 rm0090 https www st com resource en reference manual dm00031020 pdf adc dma exti gpio i2c spi tim uart stm32f446 arm cortex m4f r0p1 rm0390 https www st com resource en reference manual dm00135183 pdf adc dma exti gpio i2c spi tim uart stm32f469 arm cortex m4f r0p1 rm0386 https www st com resource en reference manual dm00127514 pdf adc dma exti gpio i2c spi tim uart stm32l4x1 arm cortex m4f r0p1 rm0394 https www st com resource en reference manual dm00151940 pdf dma exti gpio i2c rtc spi tim uart stm32l4x2 arm cortex m4f r0p1 rm0394 https www st com resource en reference manual dm00151940 pdf dma exti gpio i2c rtc spi tim uart stm32l4x3 arm cortex m4f r0p1 rm0394 https www st com resource en reference manual dm00151940 pdf dma exti gpio i2c rtc spi tim uart stm32l4x5 arm cortex m4f r0p1 rm0351 https www st com resource en reference manual dm00083560 pdf dma exti gpio i2c rtc spi tim uart stm32l4x6 arm cortex m4f r0p1 rm0351 https www st com resource en reference manual dm00083560 pdf dma exti gpio i2c rtc spi tim uart stm32l4r5 arm cortex m4f r0p1 rm0432 https www st com resource en reference manual dm00310109 pdf adc dma exti gpio i2c rtc spi tim uart stm32l4s5 arm cortex m4f r0p1 rm0432 https www st com resource en reference manual dm00310109 pdf adc dma exti gpio i2c rtc spi tim uart stm32l4r7 arm cortex m4f r0p1 rm0432 https www st com resource en reference manual dm00310109 pdf adc dma exti gpio i2c rtc spi tim uart stm32l4s7 arm cortex m4f r0p1 rm0432 https www st com resource en reference manual dm00310109 pdf adc dma exti gpio i2c rtc spi tim uart stm32l4r9 arm cortex m4f r0p1 rm0432 https www st com resource en reference manual dm00310109 pdf adc dma exti gpio i2c rtc spi tim uart stm32l4s9 arm cortex m4f r0p1 rm0432 https www st com resource en reference manual dm00310109 pdf adc dma exti gpio i2c rtc spi tim uart drone stm32 map config flag should be set at the application level according to this table documentation drone book https book drone os com api documentation https api drone os com drone stm32 map 0 15 the api documentation intentionally skips auto generated reg and thr bindings otherwise it would use several gigabytes of space and would be very slow to render in a browser one should refer to the reference manual instead and to get an idea of what the api looks like on the drone side look at the drone cortexm map module documentation usage add the crate to your cargo toml dependencies toml dependencies drone stm32 map version 0 15 0 features add or extend host feature as follows toml features host drone stm32 map host cargo rdme end license licensed under either of apache license version 2 0 license apache license apache or http www apache org licenses license 2 0 mit license license mit license mit or http opensource org licenses mit at your option contribution unless you explicitly state otherwise any contribution intentionally submitted for inclusion in the work by you as defined in the apache 2 0 license shall be dual licensed as above without any additional terms or conditions | embedded asynchronous concurrency no-std hardware-support stm32 cortex arm rtos bare-metal rust | os |
nitter | nitter test matrix https github com zedeus nitter workflows tests badge svg https github com zedeus nitter actions workflows run tests yml test matrix https github com zedeus nitter workflows docker badge svg https github com zedeus nitter actions workflows build docker yml license https img shields io github license zedeus nitter style flat license a free and open source alternative twitter front end focused on privacy and performance inspired by the invidious https github com iv org invidious project no javascript or ads all requests go through the backend client never talks to twitter prevents twitter from tracking your ip or javascript fingerprint uses twitter s unofficial api no rate limits or developer account required lightweight for nim lang https nitter net nim lang 60kb vs 784kb from twitter com rss feeds themes mobile support responsive design agplv3 licensed no proprietary instances permitted liberapay https liberapay com zedeus patreon https patreon com nitter btc bc1qp7q4qz0fgfvftm5hwz3vy284nue6jedt44kxya eth 0x66d84bc3fd031b62857ad18c62f1ba072b011925 ltc ltc1qhsz5nxw6jw9rdtw9qssjeq2h8hqk2f85rdgpkr xmr 42hkayroeaw4d6g6t8mqhpjhqcxqofjfuvfavqkenmnuzfejljacnu19i1bgddvcdn6romisscwgwjcczfle9rfhm3d1zpl roadmap embeds account system with timeline support archiving tweets profiles developer api resources the wiki contains a list of instances https github com zedeus nitter wiki instances and browser extensions https github com zedeus nitter wiki extensions maintained by the community why it s impossible to use twitter without javascript enabled for privacy minded folks preventing javascript analytics and ip based tracking is important but apart from using a vpn and ublock umatrix it s impossible despite being behind a vpn and using heavy duty adblockers you can get accurately tracked with your browser s fingerprint https restoreprivacy com browser fingerprinting no javascript required https noscriptfingerprint com this all became particularly important after twitter removed the ability https www eff org deeplinks 2020 04 twitter removes privacy option and shows why we need strong privacy laws for users to control whether their data gets sent to advertisers using an instance of nitter hosted on a vps for example you can browse twitter without javascript while retaining your privacy in addition to respecting your privacy nitter is on average around 15 times lighter than twitter and in most cases serves pages faster eg timelines load 2 4x faster in the future a simple account system will be added that lets you follow twitter users allowing you to have a clean chronological timeline without needing a twitter account screenshot nitter screenshot png installation dependencies libpcre libsass redis to compile nitter you need a nim installation see nim lang org https nim lang org install html for details it is possible to install it system wide or in the user directory you create below to compile the scss files you need to install libsass on ubuntu and debian you can use libsass dev redis is required for caching and in the future for account info it should be available on most distros as redis or redis server ubuntu debian running it with the default config is fine nitter s default config is set to use the default redis port and localhost here s how to create a nitter user clone the repo and build the project along with the scss and md files bash useradd m nitter su nitter git clone https github com zedeus nitter cd nitter nimble build d release nimble scss nimble md cp nitter example conf nitter conf set your hostname port hmac key https must be correct for cookies and redis info in nitter conf to run redis either run redis server daemonize yes or systemctl enable now redis or redis server depending on the distro run nitter by executing nitter or using the systemd service below you should run nitter behind a reverse proxy such as nginx https github com zedeus nitter wiki nginx or apache https github com zedeus nitter wiki apache for security and performance reasons docker page for the docker image https hub docker com r zedeus nitter note for arm64 support please use the separate arm64 docker image zedeus nitter latest arm64 https hub docker com r zedeus nitter tags to run nitter with docker you ll need to install and run redis separately before you can run the container see below for how to also run redis using docker to build and run nitter in docker bash docker build t nitter latest docker run v pwd nitter conf src nitter conf d network host nitter latest note for arm64 use this dockerfile dockerfile arm64 https github com zedeus nitter blob master dockerfile arm64 a prebuilt docker image is provided as well bash docker run v pwd nitter conf src nitter conf d network host zedeus nitter latest using docker compose to run both nitter and redis as different containers change redishost from localhost to nitter redis in nitter conf then run bash docker compose up d note the docker commands expect a nitter conf file in the directory you run them systemd to run nitter via systemd you can use this service file ini unit description nitter an alternative twitter front end after syslog target after network target service type simple set user and group user nitter group nitter configure location workingdirectory home nitter nitter execstart home nitter nitter nitter restart always restartsec 15 install wantedby multi user target then enable and run the service systemctl enable now nitter service logging nitter currently prints some errors to stdout and there is no real logging implemented if you re running nitter with systemd you can check stdout like this journalctl u nitter service add follow to see just the last 15 lines if you re running the docker image you can do this docker logs follow nitter container id contact feel free to join our matrix channel https matrix to nitter matrix org you can email me at zedeus pm me if you wish to contact me personally | nim twitter privacy self-hosted | front_end |
Subsets and Splits
No saved queries yet
Save your SQL queries to embed, download, and access them later. Queries will appear here once saved.