Duplicate from hasibzunair/image-recognition-demo

Co-authored-by: Hasib Zunair <hasibzunair@users.noreply.huggingface.co>

.github/workflows/check_file_size.yml

@@ -0,0 +1,16 @@
+name: Check file size
+on:               # or directly `on: [push]` to run the action on every push on any branch
+  pull_request:
+    branches: [main]
+
+  # to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check large files
+        uses: ActionsDesk/lfs-warning@v2.0
+        with:
+          filesizelimit: 10485760 # this is 10MB so we can sync to HF Spaces

.github/workflows/sync_hf.yml

@@ -0,0 +1,19 @@
+name: Sync to Hugging Face hub
+on:
+  push:
+    branches: [main]
+
+  # to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: 0
+      - name: Push to hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: git push --force https://hasibzunair:$HF_TOKEN@huggingface.co/spaces/hasibzunair/image-recognition-demo main

.gitignore

@@ -0,0 +1,129 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

README.md

@@ -0,0 +1,22 @@
+---
+title: Image Recognition Demo
+emoji: 🚀
+colorFrom: indigo
+colorTo: pink
+sdk: gradio
+sdk_version: 2.9.4
+app_file: app.py
+pinned: false
+license: afl-3.0
+duplicated_from: hasibzunair/image-recognition-demo
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference
+
+# Image Recognition Demo
+Code for a simple demo of an image recognition system built with Gradio and served on HuggingFace Spaces. App is live at https://huggingface.co/spaces/hasibzunair/image-recognition-demo.
+
+### References
+* https://huggingface.co/docs/hub/spaces-github-actions
+* https://www.gradio.app/image_classification_in_pytorch/
+* GH Actions https://youtu.be/8hOzsFETm4I

app.py

@@ -0,0 +1,74 @@
+import os
+import torch
+import gradio as gr
+
+from PIL import Image
+from torchvision import transforms
+
+
+"""
+Built following:
+https://huggingface.co/spaces/pytorch/ResNet/tree/main
+https://www.gradio.app/image_classification_in_pytorch/
+"""
+
+# Get classes list
+os.system("wget https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt")
+
+# Load PyTorch model
+model = torch.hub.load('pytorch/vision:v0.10.0', 'resnet18', pretrained=True)
+model.eval()
+
+# Download an example image from the pytorch website
+torch.hub.download_url_to_file("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
+
+# Inference!
+def inference(input_image):
+    preprocess = transforms.Compose([
+        transforms.Resize(256),
+        transforms.CenterCrop(224),
+        transforms.ToTensor(),
+        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+    ])
+    input_tensor = preprocess(input_image)
+    input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model
+
+    # Move the input and model to GPU for speed if available
+    if torch.cuda.is_available():
+        input_batch = input_batch.to('cuda')
+        model.to('cuda')
+
+    with torch.no_grad():
+        output = model(input_batch)
+    # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
+    probabilities = torch.nn.functional.softmax(output[0], dim=0)
+
+    # Read the categories
+    with open("imagenet_classes.txt", "r") as f:
+        categories = [s.strip() for s in f.readlines()]
+    # Show top categories per image
+    top5_prob, top5_catid = torch.topk(probabilities, 5)
+    result = {}
+    for i in range(top5_prob.size(0)):
+        result[categories[top5_catid[i]]] = top5_prob[i].item()
+    return result
+
+# Define ins outs placeholders
+inputs = gr.inputs.Image(type='pil')
+outputs = gr.outputs.Label(type="confidences",num_top_classes=5)
+
+# Define style
+title = "Image Recognition Demo"
+description = "This is a prototype application which demonstrates how artifical intelligence based systems can recognize what object(s) is present in an image. This fundamental task in computer vision known as `Image Classification` has applications stretching from autonomous vehicles to medical imaging. To use it, simply upload your image, or click one of the examples images to load them, which I took at <a href='https://espacepourlavie.ca/en/biodome' target='_blank'>Montréal Biodôme</a>! Read more at the links below."
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/1512.03385' target='_blank'>Deep Residual Learning for Image Recognition</a> | <a href='https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py' target='_blank'>Github Repo</a></p>"
+
+# Run inference
+gr.Interface(inference, 
+            inputs, 
+            outputs, 
+            examples=["example1.jpg", "example2.jpg"], 
+            title=title, 
+            description=description, 
+            article=article,
+            analytics_enabled=False).launch()
+

requirements.txt

@@ -0,0 +1,3 @@
+torch
+torchvision
+Pillow