Upload 16 files

.streamlit/config.toml

@@ -0,0 +1,3 @@
+[theme]
+base="light"
+primaryColor="#29B4E8"

Demo.py

@@ -0,0 +1,122 @@
+import streamlit as st
+import sparknlp
+import os
+import pandas as pd
+
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+from sparknlp.pretrained import PretrainedPipeline
+from streamlit_tags import st_tags
+
+# Page configuration
+st.set_page_config(
+    layout="wide", 
+    initial_sidebar_state="auto"
+)
+
+# CSS for styling
+st.markdown("""
+    <style>
+        .main-title {
+            font-size: 36px;
+            color: #4A90E2;
+            font-weight: bold;
+            text-align: center;
+        }
+        .section {
+            background-color: #f9f9f9;
+            padding: 10px;
+            border-radius: 10px;
+            margin-top: 10px;
+        }
+        .section p, .section ul {
+            color: #666666;
+        }
+    </style>
+""", unsafe_allow_html=True)
+
+@st.cache_resource
+def init_spark():
+    return sparknlp.start()
+
+@st.cache_resource
+def create_pipeline(model):
+    imageAssembler = ImageAssembler() \
+        .setInputCol("image") \
+        .setOutputCol("image_assembler")
+
+    imageClassifier = ConvNextForImageClassification \
+        .pretrained("image_classifier_convnext_tiny_224_local", "en") \
+        .setInputCols(["image_assembler"]) \
+        .setOutputCol("class")
+
+    pipeline = Pipeline(stages=[image_assembler, imageClassifier])
+    return pipeline
+
+def fit_data(pipeline, data):
+    empty_df = spark.createDataFrame([['']]).toDF('text')
+    model = pipeline.fit(empty_df)
+    light_pipeline = LightPipeline(model)
+    annotations_result = light_pipeline.fullAnnotateImage(data)
+    return annotations_result[0]['class'][0].result
+
+def save_uploadedfile(uploadedfile):
+    filepath = os.path.join(IMAGE_FILE_PATH, uploadedfile.name)
+    with open(filepath, "wb") as f:
+        if hasattr(uploadedfile, 'getbuffer'):
+            f.write(uploadedfile.getbuffer())
+        else:
+            f.write(uploadedfile.read())
+        
+# Sidebar content
+model_list = ['image_classifier_convnext_tiny_224_local']
+model = st.sidebar.selectbox(
+    "Choose the pretrained model",
+    model_list,
+    help="For more info about the models visit: https://sparknlp.org/models"
+)
+
+# Set up the page layout
+st.markdown(f'<div class="main-title">ConvNext For Image Classification</div>', unsafe_allow_html=True)
+# st.markdown(f'<div class="section"><p>{sub_title}</p></div>', unsafe_allow_html=True)
+
+# Reference notebook link in sidebar
+link = """
+<a href="https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/annotation/image/ConvNextForImageClassification.ipynb">
+    <img src="https://colab.research.google.com/assets/colab-badge.svg" style="zoom: 1.3" alt="Open In Colab"/>
+</a>
+"""
+st.sidebar.markdown('Reference notebook:')
+st.sidebar.markdown(link, unsafe_allow_html=True)
+
+# Load examples
+IMAGE_FILE_PATH = f"inputs"
+image_files = sorted([file for file in os.listdir(IMAGE_FILE_PATH) if file.split('.')[-1]=='png' or file.split('.')[-1]=='jpg' or file.split('.')[-1]=='JPEG' or file.split('.')[-1]=='jpeg'])
+
+img_options = st.selectbox("Select an image", image_files)
+uploadedfile = st.file_uploader("Try it for yourself!")
+
+if uploadedfile:
+    file_details = {"FileName":uploadedfile.name,"FileType":uploadedfile.type}
+    save_uploadedfile(uploadedfile)
+    selected_image = f"{IMAGE_FILE_PATH}/{uploadedfile.name}"
+elif img_options:
+    selected_image = f"{IMAGE_FILE_PATH}/{img_options}"
+
+st.subheader('Classified Image')
+
+image_size = st.slider('Image Size', 400, 1000, value=400, step = 100)
+
+try:
+    st.image(f"{IMAGE_FILE_PATH}/{selected_image}", width=image_size)
+except:
+    st.image(selected_image, width=image_size)
+
+st.subheader('Classification')
+
+spark = init_spark()
+Pipeline = create_pipeline(model)
+output = fit_data(Pipeline, selected_image)
+
+st.markdown(f'This document has been classified as  : **{output}**')

Dockerfile

@@ -0,0 +1,70 @@
+# Download base image ubuntu 18.04
+FROM ubuntu:18.04
+
+# Set environment variables
+ENV NB_USER jovyan
+ENV NB_UID 1000
+ENV HOME /home/${NB_USER}
+
+# Install required packages
+RUN apt-get update && apt-get install -y \
+    tar \
+    wget \
+    bash \
+    rsync \
+    gcc \
+    libfreetype6-dev \
+    libhdf5-serial-dev \
+    libpng-dev \
+    libzmq3-dev \
+    python3 \
+    python3-dev \
+    python3-pip \
+    unzip \
+    pkg-config \
+    software-properties-common \
+    graphviz \
+    openjdk-8-jdk \
+    ant \
+    ca-certificates-java \
+    && apt-get clean \
+    && update-ca-certificates -f;
+
+# Install Python 3.8 and pip
+RUN add-apt-repository ppa:deadsnakes/ppa \
+    && apt-get update \
+    && apt-get install -y python3.8 python3-pip \
+    && apt-get clean;
+
+# Set up JAVA_HOME
+ENV JAVA_HOME /usr/lib/jvm/java-8-openjdk-amd64/
+RUN mkdir -p ${HOME} \
+    && echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/" >> ${HOME}/.bashrc \
+    && chown -R ${NB_UID}:${NB_UID} ${HOME}
+
+# Create a new user named "jovyan" with user ID 1000
+RUN useradd -m -u ${NB_UID} ${NB_USER}
+
+# Switch to the "jovyan" user
+USER ${NB_USER}
+
+# Set home and path variables for the user
+ENV HOME=/home/${NB_USER} \
+    PATH=/home/${NB_USER}/.local/bin:$PATH
+
+# Set the working directory to the user's home directory
+WORKDIR ${HOME}
+
+# Upgrade pip and install Python dependencies
+RUN python3.8 -m pip install --upgrade pip
+COPY requirements.txt /tmp/requirements.txt
+RUN python3.8 -m pip install -r /tmp/requirements.txt
+
+# Copy the application code into the container at /home/jovyan
+COPY --chown=${NB_USER}:${NB_USER} . ${HOME}
+
+# Expose port for Streamlit
+EXPOSE 7860
+
+# Define the entry point for the container
+ENTRYPOINT ["streamlit", "run", "Demo.py", "--server.port=7860", "--server.address=0.0.0.0"]

pages/Workflow & Model Overview.py

@@ -0,0 +1,254 @@
+import streamlit as st
+
+# Custom CSS for better styling
+st.markdown("""
+    <style>
+        .main-title {
+            font-size: 36px;
+            color: #4A90E2;
+            font-weight: bold;
+            text-align: center;
+        }
+        .sub-title {
+            font-size: 24px;
+            color: #4A90E2;
+            margin-top: 20px;
+        }
+        .section {
+            background-color: #f9f9f9;
+            padding: 15px;
+            border-radius: 10px;
+            margin-top: 20px;
+        }
+        .section h2 {
+            font-size: 22px;
+            color: #4A90E2;
+        }
+        .section p, .section ul {
+            color: #666666;
+        }
+        .link {
+            color: #4A90E2;
+            text-decoration: none;
+        }
+        .benchmark-table {
+            width: 100%;
+            border-collapse: collapse;
+            margin-top: 20px;
+        }
+        .benchmark-table th, .benchmark-table td {
+            border: 1px solid #ddd;
+            padding: 8px;
+            text-align: left;
+        }
+        .benchmark-table th {
+            background-color: #4A90E2;
+            color: white;
+        }
+        .benchmark-table td {
+            background-color: #f2f2f2;
+        }
+    </style>
+""", unsafe_allow_html=True)
+
+# Main Title
+st.markdown('<div class="main-title">ConvNeXT Image Classification</div>', unsafe_allow_html=True)
+
+# Description
+st.markdown("""
+<div class="section">
+    <p><strong>ConvNeXT</strong> is a state-of-the-art image classification model developed by Facebook. The model <strong>ConvNextForImageClassification</strong> can load ConvNeXT models that compete favorably with Transformers in terms of accuracy and scalability, achieving 87.8% ImageNet top-1 accuracy and outperforming Swin Transformers on COCO detection and ADE20K segmentation, while maintaining the simplicity and efficiency of standard ConvNets.</p>
+    <p>This annotator is compatible with all the models trained/fine-tuned by using ConvNextForImageClassification for PyTorch or TFConvNextForImageClassification for TensorFlow models in Hugging Face.</p>
+    <p>The model used in this demo is <code>image_classifier_convnext_tiny_224_local</code>, adapted from Hugging Face and curated for scalability and production-readiness using Spark NLP.</p>
+</div>
+""", unsafe_allow_html=True)
+
+# Image Classification Overview
+st.markdown('<div class="sub-title">What is Image Classification?</div>', unsafe_allow_html=True)
+st.markdown("""
+<div class="section">
+    <p><strong>Image Classification</strong> is a computer vision task where an algorithm is trained to recognize and classify objects within images. This process involves assigning a label or category to an image based on its visual content.</p>
+    <h2>How It Works</h2>
+    <p>Image classification typically involves the following steps:</p>
+    <ul>
+        <li><strong>Data Collection</strong>: Gather a dataset of labeled images.</li>
+        <li><strong>Preprocessing</strong>: Normalize and resize images to prepare them for the model.</li>
+        <li><strong>Model Training</strong>: Use a machine learning model, such as ConvNeXT, to learn patterns and features from the images.</li>
+        <li><strong>Inference</strong>: Apply the trained model to new images to predict their labels.</li>
+    </ul>
+    <h2>Why Use Image Classification?</h2>
+    <p>Image classification can automate and streamline many tasks, such as:</p>
+    <ul>
+        <li>Identifying objects in photos for content tagging.</li>
+        <li>Enhancing search functionality by categorizing images.</li>
+        <li>Supporting autonomous systems like self-driving cars.</li>
+    </ul>
+    <h2>Applications</h2>
+    <p>Applications of image classification span across various industries:</p>
+    <ul>
+        <li><strong>Healthcare</strong>: Diagnosing diseases from medical images.</li>
+        <li><strong>Retail</strong>: Sorting and tagging product images.</li>
+        <li><strong>Security</strong>: Facial recognition for authentication.</li>
+    </ul>
+    <h2>Importance</h2>
+    <p>Image classification is crucial because it enables machines to interpret visual data, which is essential for creating intelligent systems capable of understanding and interacting with the world in a more human-like manner.</p>
+    <p>The <strong>ConvNeXT</strong> model used in this example is a state-of-the-art approach for image classification, offering advanced performance and scalability. It utilizes convolutional architecture to capture intricate patterns and relationships within images, enhancing classification accuracy and efficiency.</p>
+</div>
+""", unsafe_allow_html=True)
+
+# How to Use
+st.markdown('<div class="sub-title">How to Use the Model</div>', unsafe_allow_html=True)
+st.code('''
+import sparknlp
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+
+# Load image data
+imageDF = spark.read \\
+    .format("image") \\
+    .option("dropInvalid", value = True) \\
+    .load("src/test/resources/image/")
+
+# Define Image Assembler
+imageAssembler = ImageAssembler() \\
+    .setInputCol("image") \\
+    .setOutputCol("image_assembler")
+
+# Define ConvNeXT classifier
+imageClassifier = ConvNextForImageClassification \\
+    .pretrained("image_classifier_convnext_tiny_224_local", "en") \\
+    .setInputCols(["image_assembler"]) \\
+    .setOutputCol("class")
+
+# Create pipeline
+pipeline = Pipeline().setStages([imageAssembler, imageClassifier])
+
+# Apply pipeline to image data
+pipelineDF = pipeline.fit(imageDF).transform(imageDF)
+
+# Show results
+pipelineDF \\
+  .selectExpr("reverse(split(image.origin, '/'))[0] as image_name", "class.result") \\
+  .show(truncate=False)
+''', language='python')
+
+# Results
+st.markdown('<div class="sub-title">Results</div>', unsafe_allow_html=True)
+st.markdown("""
+<div class="section">
+    <table class="benchmark-table">
+        <tr>
+            <th>Image Name</th>
+            <th>Result</th>
+        </tr>
+        <tr>
+            <td>dog.JPEG</td>
+            <td>[whippet]</td>
+        </tr>
+        <tr>
+            <td>cat.JPEG</td>
+            <td>[Siamese]</td>
+        </tr>
+        <tr>
+            <td>bird.JPEG</td>
+            <td>[peacock]</td>
+        </tr>
+    </table>
+</div>
+""", unsafe_allow_html=True)
+
+# Model Information
+st.markdown('<div class="sub-title">Model Information</div>', unsafe_allow_html=True)
+st.markdown("""
+<div class="section">
+    <table class="benchmark-table">
+        <tr>
+            <th>Attribute</th>
+            <th>Description</th>
+        </tr>
+        <tr>
+            <td><strong>Model Name</strong></td>
+            <td>image_classifier_convnext_tiny_224_local</td>
+        </tr>
+        <tr>
+            <td><strong>Compatibility</strong></td>
+            <td>Spark NLP 5.0.0+</td>
+        </tr>
+        <tr>
+            <td><strong>License</strong></td>
+            <td>Open Source</td>
+        </tr>
+        <tr>
+            <td><strong>Edition</strong></td>
+            <td>Official</td>
+        </tr>
+        <tr>
+            <td><strong>Input Labels</strong></td>
+            <td>[image_assembler]</td>
+        </tr>
+        <tr>
+            <td><strong>Output Labels</strong></td>
+            <td>[class]</td>
+        </tr>
+        <tr>
+            <td><strong>Language</strong></td>
+            <td>en</td>
+        </tr>
+        <tr>
+            <td><strong>Size</strong></td>
+            <td>107.6 MB</td>
+        </tr>
+    </table>
+</div>
+""", unsafe_allow_html=True)
+
+# Predicted Entities
+st.markdown('<div class="sub-title">Predicted Entities</div>', unsafe_allow_html=True)
+st.markdown("""
+<div class="section">
+    <ul>
+        <li>turnstile</li>
+        <li>damselfly</li>
+        <li>mixing bowl</li>
+        <li>sea snake</li>
+        <li>cockroach</li>
+        <li>...and many more</li>
+    </ul>
+</div>
+""", unsafe_allow_html=True)
+
+# Data Source Section
+st.markdown('<div class="sub-title">Data Source</div>', unsafe_allow_html=True)
+st.markdown("""
+<div class="section">
+    <p>The ConvNeXT model is available on <a class="link" href="https://huggingface.co/models" target="_blank">Hugging Face</a>. This model was trained on a large dataset of images and can be used for accurate image classification.</p>
+</div>
+""", unsafe_allow_html=True)
+
+# References
+st.markdown('<div class="sub-title">References</div>', unsafe_allow_html=True)
+st.markdown("""
+<div class="section">
+    <ul>
+        <li><a class="link" href="https://sparknlp.org/2023/07/05/image_classifier_convnext_tiny_224_local_en.html" target="_blank" rel="noopener">ConvNeXT Model on Spark NLP</a></li>
+        <li><a class="link" href="https://huggingface.co/facebook/convnext-tiny-224" target="_blank" rel="noopener">ConvNeXT Model on Hugging Face</a></li>
+        <li><a class="link" href="https://github.com/facebookresearch/ConvNeXT" target="_blank" rel="noopener">ConvNeXT GitHub Repository</a></li>
+        <li><a class="link" href="https://arxiv.org/abs/2201.03545" target="_blank" rel="noopener">ConvNeXT Paper</a></li>
+    </ul>
+</div>
+""", unsafe_allow_html=True)
+
+# Community & Support
+st.markdown('<div class="sub-title">Community & Support</div>', unsafe_allow_html=True)
+st.markdown("""
+<div class="section">
+    <ul>
+        <li><a class="link" href="https://sparknlp.org/" target="_blank">Official Website</a>: Documentation and examples</li>
+        <li><a class="link" href="https://join.slack.com/t/spark-nlp/shared_invite/zt-198dipu77-L3UWNe_AJ8xqDk0ivmih5Q" target="_blank">Slack</a>: Live discussion with the community and team</li>
+        <li><a class="link" href="https://github.com/JohnSnowLabs/spark-nlp" target="_blank">GitHub</a>: Bug reports, feature requests, and contributions</li>
+        <li><a class="link" href="https://medium.com/spark-nlp" target="_blank">Medium</a>: Spark NLP articles</li>
+        <li><a class="link" href="https://www.youtube.com/channel/UCmFOjlpYEhxf_wJUDuz6xxQ/videos" target="_blank">YouTube</a>: Video tutorials</li>
+    </ul>
+</div>
+""", unsafe_allow_html=True)

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+streamlit-tags
+pandas
+numpy
+spark-nlp
+pyspark