Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
11
1
34
Santiago Castro
bryant1410
Follow
rwightman's profile picture
filevich's profile picture
Molbap's profile picture
3 followers
ยท
13 following
https://santi.uy
bryant1410
bryant1410
AI & ML interests
Vision and Language, Humor, Sarcasm.
Recent Activity
reacted
to
rwightman
's
post
with ๐
about 1 month ago
Want to validate some hparams or figure out what `timm` model to use before commiting to download or training with a large dataset? Try mini-imagenet: https://huggingface.co/datasets/timm/mini-imagenet I had this sitting on my drive and forgot where I pulled it together from. It's 100 classes of imagenet, 50k train and 10k val images (from ImageNet-1k train set), and 5k test images (from ImageNet-1k val set). 7.4GB instead of > 100GB for the full ImageNet-1k. This ver is not reduced resolution like some other 'mini' versions. Super easy to use with timm train/val scripts, checkout the dataset card. I often check fine-tuning with even smaller datasets like: * https://huggingface.co/datasets/timm/resisc45 * https://huggingface.co/datasets/timm/oxford-iiit-pet But those are a bit small to train any modest size model w/o starting from pretrained weights.
View all activity
Organizations
Papers
13
arxiv:
2402.15021
arxiv:
2305.18786
arxiv:
2305.12544
arxiv:
2210.02399
Expand 13 papers
models
1
bryant1410/xlm-roberta-base-finetuned-quales
Question Answering
โข
Updated
Oct 20, 2023
โข
26
datasets
1
bryant1410/moments-in-time
Updated
Jul 17
โข
5