This project implements a real time object detection via webcam and image detection using YOLO algorithm. YOLO is a object detection algorithm which stand for You Only Look Once. I've implemented the algorithm from scratch in PyTorch using pre-trained weights. YOLOv3 was published in research paper: YOLOv3: An Incremental Improvement: Joseph Redmon, Ali Farhadi. It's originally implemented in YOLOv3.
COCO dataset is used for training.
Real time detection can be use via command prompt or GUI.
- Clone the repository
git clone https://github.com/PankajJ08/Real-Time-Object-Detection-using-YOLO-v3.git
- Move to the directory
cd Real-Time-Object-Detection-using-YOLO-v3
- To infer on an image that is stored on your local machine
python3 img_detect.py --image path='/path/to/image/'
- To use in real-time on webcam
python3 camera.py
- To use GUI for real-time detection
python gui.py
** Download the official weight file and place it under a folder called weight.
