Finalize project structure, update URLs, and clean up for deployment

Author: HarithKavish

.github/workflows/train-and-upload.yml

@@ -0,0 +1,43 @@
+# GitHub Actions workflow for training and uploading models to Hugging Face Hub
+# Place this file in .github/workflows/train-and-upload.yml
+
+name: Train and Upload Model to Hugging Face Hub
+
+on:
+  push:
+    branches: [main]
+  workflow_dispatch:
+
+jobs:
+  train-and-upload:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          lfs: true
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+          pip install huggingface_hub tensorflowjs
+
+      - name: Train model (replace with your script)
+        run: |
+          python main.py  # or your training script
+
+      - name: Convert Keras model to TensorFlow.js
+        run: |
+          tensorflowjs_converter --input_format=keras image_classifier.keras tfjs_model/
+
+      - name: Upload models to Hugging Face Hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: |
+          python scripts/upload_to_hub.py

.gitignore

@@ -0,0 +1,75 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# 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
+debug.log
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# mypy
+.mypy_cache/
+.dmypy.json
+
+# VS Code
+.vscode/
+
+# Local model artifacts
+model/
+models/
+tfjs_model/
+*.keras
+*.h5
+*.pt
+*.pth
+
+# System files
+.DS_Store
+Thumbs.db

README.md

@@ -1,4 +1,3 @@
-<<<<<<< HEAD
 ---
 title: Multi-Object Detection using YOLO
 emoji: 🦾
@@ -9,66 +8,18 @@ app_file: app.py
 pinned: false
 ---
 
-# Multi-Object Detection API (YOLO + CNN)
-
-A FastAPI backend for multi-object detection and image classification using YOLOv8 and a custom CNN. Deployable on Hugging Face Spaces.
-
-## API Endpoints
-
-- **POST `/detect-object`**: Upload an image (form-data, key: `file`). Returns detected objects, their counts, and CNN class prediction.
-- **GET `/health`**: Health check endpoint. Returns `{ "status": "ok" }`.
-
-## Deployment
-- All files (`app.py`, `requirements.txt`, `space.yaml`, `image_classifier.keras`, `yolov8n-seg.pt`) must be in the repo.
-- Deploy on Hugging Face Spaces with FastAPI SDK.
-
-## Example (Python)
-```python
-import requests
-files = {'file': open('your_image.jpg', 'rb')}
-r = requests.post('https://your-space-url.hf.space/detect-object', files=files)
-print(r.json())
-```
-=======
 # Multi-Object Detection using YOLO and Custom CNN
 
-This project performs real-time multi-object detection and image classification using YOLOv8 and a custom-trained CNN on CIFAR-10. It captures webcam video, detects objects, classifies images, and displays results live.
+A robust, cloud-ready multi-object detection system using FastAPI, YOLOv8, and a custom CNN. Supports MLOps, edge (browser) inference, and cloud deployment.
 
-## Video Preview
-Original Video Speed: 0.5X
-
-[![Demo Video](https://github.com/user-attachments/assets/22620da8-8508-4100-b455-af382fc313c5)](https://github.com/user-attachments/assets/22620da8-8508-4100-b455-af382fc313c5)
-
-## Features
-- Real-time object detection using YOLOv8 segmentation
-- Image classification using a custom CNN trained on CIFAR-10
-- Live webcam video processing
-- Model saving and loading
-
-## Requirements
-Install dependencies with:
-```bash
-pip install -r requirements.txt
-```
+- **Backend:** FastAPI (`app.py`)
+- **Frontend:** TensorFlow.js demo (`tfjs_demo/index.html`)
+- **Model Hub:** [Hugging Face Model Repo](https://huggingface.co/harithkavish/SkinNet-Analyzer)
+- **Spaces Demo:** [Hugging Face Spaces](https://huggingface.co/spaces/harithkavish/Multi-Object-Detection-using-YOLO)
 
 ## Usage
-1. Clone the repository and navigate to the project folder.
-2. Ensure you have a webcam connected.
-3. Run the main script:
-   ```bash
-   python main.py
-   ```
-4. Follow the prompts to train the model and start detection.
-5. Press 'q' to quit the video window.
+- Run the backend: `uvicorn app:app`
+- Try the browser demo: open `tfjs_demo/index.html`
+- See `.github/workflows/train-and-upload.yml` for CI/CD
 
-## Files
-- `main.py`: Main script for training and detection
-- `yolov8n-seg.pt`: YOLOv8 model weights
-- `image_classifier.keras`: Saved CNN model
-- `requirements.txt`: Python dependencies
-
-## Contributors
-- Harith Kavish S
-- Sharwan Krishnan P
-- Sanjay R
->>>>>>> 1c3894d2065701b19ab2a500433a6d7f7a075d13
+---

app.py

@@ -25,7 +25,7 @@
 
 # Load CNN model
 try:
-    keras_model_path = hf_hub_download(repo_id="harithkavish/multi-object-detection-models", filename="image_classifier.keras")
+    keras_model_path = hf_hub_download(repo_id="harithkavish/SkinNet-Analyzer", filename="image_classifier.keras")
     cnn_model = keras.models.load_model(keras_model_path)
 except Exception as e:
     from tensorflow import keras as keras_build
@@ -114,7 +114,7 @@ def patched_load(*args, **kwargs):
 
 # Load YOLOv8 model robustly
 try:
-    yolo_model_path = hf_hub_download(repo_id="harithkavish/multi-object-detection-models", filename="yolov8n-seg.pt")
+    yolo_model_path = hf_hub_download(repo_id="harithkavish/SkinNet-Analyzer", filename="yolov8n-seg.pt")
     yolo_model = load_yolo_model(yolo_model_path)
 except Exception as e:
     print('Error in YOLO model loading logic:', e)