Update README.md

README.md

@@ -1,326 +1,10 @@
-# Wall Color Visualizer - Backend
-
-A FastAPI backend service that uses Meta's Segment Anything Model (SAM) for intelligent wall segmentation and color visualization.
-
-## Features
-
-- **AI-Powered Segmentation**: Uses Meta's SAM model for accurate object segmentation
-- **Fallback Support**: Traditional CV methods when SAM is unavailable
-- **Color Application**: Real-time color overlay with adjustable opacity
-- **REST API**: Clean and well-documented API endpoints
-- **CORS Enabled**: Ready for cross-origin requests from Flutter app
-
-## Prerequisites
-
-- Python 3.8 or higher
-- CUDA-capable GPU (optional, for faster processing)
-- At least 8GB RAM
-- 5GB free disk space (for SAM model)
-
-## Installation
-
-### 1. Clone or Navigate to Backend Directory
-
-```bash
-cd /media/aliroohan/hello/MAD/project/backend
-```
-
-### 2. Create Virtual Environment
-
-```bash
-python3 -m venv venv
-source venv/bin/activate  # On Windows: venv\Scripts\activate
-```
-
-### 3. Install Dependencies
-
-```bash
-pip install --upgrade pip
-pip install -r requirements.txt
-```
-
-### 4. Download SAM Model
-
-Download the SAM model checkpoint (choose one based on your needs):
-
-**Option 1: Largest and Most Accurate (vit_h - 2.4GB)**
-```bash
-wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth
-```
-
-**Option 2: Medium (vit_l - 1.2GB)**
-```bash
-wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth
-```
-
-**Option 3: Smallest and Fastest (vit_b - 375MB)**
-```bash
-wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth
-```
-
-If using a different model, update `sam_checkpoint` and `model_type` in `main.py`.
-
-### 5. Quick Setup (All-in-One)
-
-Alternatively, run the setup script:
-
-```bash
-chmod +x setup.sh
-./setup.sh
-```
-
-## Running the Server
-
-### Development Mode
-
-```bash
-uvicorn main:app --reload --host 0.0.0.0 --port 8000
-```
-
-### Production Mode
-
-```bash
-uvicorn main:app --host 0.0.0.0 --port 8000 --workers 4
-```
-
-The server will start at `http://localhost:8000`
-
-## API Endpoints
-
-### Health Check
-
-**GET** `/health`
-
-Check if the server and SAM model are loaded.
-
-**Response:**
-```json
-{
-  "status": "healthy",
-  "device": "cuda",
-  "sam_model_loaded": true
-}
-```
-
-### Automatic Segmentation
-
-**POST** `/segment-automatic`
-
-Automatically segments all objects in the image.
-
-**Request:**
-- Content-Type: `multipart/form-data`
-- Body: `file` (image file)
-
-**Response:**
-```json
-{
-  "success": true,
-  "num_masks": 5,
-  "masks": [
-    {
-      "id": 0,
-      "mask_base64": "...",
-      "area": 50000,
-      "bbox": [x, y, width, height]
-    }
-  ],
-  "image_base64": "..."
-}
-```
-
-### Simple Segmentation (Fallback)
-
-**POST** `/simple-segment`
-
-Uses traditional CV methods for segmentation.
-
-Same request/response format as `/segment-automatic`.
-
-### Point-Based Segmentation
-
-**POST** `/segment-point`
-
-Segments object at a specific point in the image.
-
-**Request:**
-```json
-{
-  "image_base64": "...",
-  "point_x": 100.5,
-  "point_y": 200.5
-}
-```
-
-**Response:**
-```json
-{
-  "success": true,
-  "mask_base64": "...",
-  "score": 0.95
-}
-```
-
-### Apply Color
-
-**POST** `/apply-color`
-
-Applies color to a masked region.
-
-**Request:**
-```json
-{
-  "image_base64": "...",
-  "mask_base64": "...",
-  "color_hex": "#FF5733",
-  "opacity": 0.8
-}
-```
-
-**Response:**
-```json
-{
-  "success": true,
-  "result_base64": "..."
-}
-```
-
-## Configuration
-
-### Environment Variables
-
-Create a `.env` file (see `.env.example`):
-
-```env
-HOST=0.0.0.0
-PORT=8000
-SAM_CHECKPOINT=sam_vit_h_4b8939.pth
-MODEL_TYPE=vit_h
-DEVICE=cuda  # or 'cpu'
-```
-
-### Model Selection
-
-In `main.py`, modify:
-
-```python
-sam_checkpoint = "sam_vit_h_4b8939.pth"  # Path to model
-model_type = "vit_h"  # vit_h, vit_l, or vit_b
-device = "cuda"  # cuda or cpu
-```
-
-## Troubleshooting
-
-### CUDA Out of Memory
-
-If you encounter CUDA memory errors:
-
-1. Use a smaller model (vit_b)
-2. Reduce image size in Flutter app
-3. Use CPU instead: `device = "cpu"`
-
-### Model Not Loading
-
-1. Verify checkpoint file exists in the correct location
-2. Check file integrity (download again if needed)
-3. Ensure sufficient RAM/VRAM
-
-### Slow Performance
-
-- Use GPU (CUDA) instead of CPU
-- Reduce image resolution
-- Use smaller model (vit_b)
-
-## Testing
-
-### Test with cURL
-
-```bash
-# Health check
-curl http://localhost:8000/health
-
-# Upload and segment
-curl -X POST -F "file=@test_image.jpg" \
-  http://localhost:8000/segment-automatic
-```
-
-### Test with Python
-
-```python
-import requests
-
-# Health check
-response = requests.get('http://localhost:8000/health')
-print(response.json())
-
-# Segment image
-with open('test_image.jpg', 'rb') as f:
-    files = {'file': f}
-    response = requests.post(
-        'http://localhost:8000/segment-automatic',
-        files=files
-    )
-    print(response.json())
-```
-
-## Performance
-
-### With CUDA (GPU)
-- Segmentation: 2-5 seconds per image
-- Color application: < 1 second
-
-### Without CUDA (CPU)
-- Segmentation: 10-30 seconds per image
-- Color application: < 1 second
-
-## Network Configuration
-
-### For Android Emulator
-Use: `http://10.0.2.2:8000`
-
-### For iOS Simulator
-Use: `http://localhost:8000`
-
-### For Real Devices
-1. Find your computer's IP address:
-   ```bash
-   # Linux/Mac
-   ip addr show
-   # or
-   ifconfig
-   
-   # Windows
-   ipconfig
-   ```
-
-2. Use: `http://YOUR_IP:8000`
-3. Ensure firewall allows port 8000
-
-## Dependencies
-
-- **fastapi**: Web framework
-- **uvicorn**: ASGI server
-- **segment-anything**: Meta's SAM model
-- **torch**: PyTorch for deep learning
-- **opencv-python**: Image processing
-- **pillow**: Image manipulation
-- **numpy**: Numerical operations
-
-## License
-
-This project uses Meta's Segment Anything Model. See SAM's license for details.
-
-## Support
-
-For issues or questions:
-1. Check the troubleshooting section
-2. Verify all dependencies are installed
-3. Ensure the model is downloaded correctly
-4. Check server logs for detailed error messages
-
-## Credits
-
-- Meta AI for the Segment Anything Model
-- FastAPI framework
-- OpenCV community
-
+---
+title: Wallpaint
+emoji: 🌖
+colorFrom: blue
+colorTo: purple
+sdk: docker
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference