Setup Dockerfile and fixed detectron2 installation

README.md

@@ -4,57 +4,10 @@ emoji: 🚗
 colorFrom: gray
 colorTo: pink
 sdk: gradio
-sdk_version: 3.50.0
+sdk_version: 5.25.2
 app_file: app.py
 pinned: false
 license: apache-2.0
 ---
 
-# Car Damage Insurance Fraud Detector
-
-A sophisticated AI-powered system that detects car damage and potential insurance fraud using deep learning models.
-
-## Features
-
-- Damage Detection: Identifies and localizes car damage using Detectron2
-- Deepfake Detection: Analyzes images for potential manipulation
-- User-friendly Interface: Built with Gradio for easy interaction
-- Multi-device Support: Works on CPU, CUDA, and MPS (Apple Silicon)
-
-## Requirements
-
-- Python 3.8+
-- PyTorch
-- OpenCV
-- Gradio
-- Detectron2 (optional, not available for macOS)
-
-## Installation
-
-1. Clone the repository
-2. Install dependencies:
-```bash
-pip install -r requirements.txt
-```
-
-## Usage
-
-1. Run the application:
-```bash
-python app.py
-```
-
-2. Open your browser and navigate to the provided local URL
-
-## Model Requirements
-
-- Damage detection model (Detectron2 format)
-- Deepfake detection model (custom format)
-
-## License
-
-Apache 2.0
-
-## Note
-
-This application requires pre-trained models for both damage detection and deepfake detection. Make sure to have the appropriate model files in the correct locations before running the application.
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference