README.md

metadata

title: Yolo V3
emoji: 👀
colorFrom: gray
colorTo: blue
sdk: gradio
sdk_version: 3.40.1
app_file: app.py
pinned: false
license: mit

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

YoloV3 object detection model- Interactive Interface

This project Impliments a simple Gradio interface to perform inference on YoloV3 object detection.

Task :

The task involves performing detection on the Pascal voc dataset using the YoloV3 model built with PyTorch and PyTorch Lightning.

Files :

1. requirements.txt: Contains the necessary packages required for installation.
2. model.py: Contains the YoloV3 model architecture.
3. YoloV3.pth: Trained model checkpoint file containing model weights.
4. examples/: Folder containing example images (e.g., car.jpg, home.jpg, etc.).
5. app.py: Contains the Gradio code for the interactive interface. Users can select input images or examples of the model that detects objects.

Implementation

The following features are implemented using Gradio:

1. Upload and Select Images: Users can upload new images or select from a set of example images.

Usage

1. Run the app.py script to launch the interactive Gradio interface.