This project consists in implementing a pipeline for automatic face detection, cropping and resizing into the given shapes for profile pictures, using Pytorch and a pre-trained Yolov7 detection model imported from WongKinYiu/yolov7 (https://github.com/WongKinYiu/yolov7).
The file may be too large for visualization directly on GitHub; it is recommended to download and view it locally for better performance.
- Wang, Chien-Yao, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023.