fine-tuning Yolov9 for face recognition

WongKinYiu / yolov9

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

GNU General Public License v3.0

8.94k stars 1.41k forks source link

fine-tuning Yolov9 for face recognition #85

Open kiashann opened 8 months ago

kiashann commented 8 months ago

Hi, I want to use Yolov9 for face recognition task. First of all, is it possible to use pre-training model for this task? I mean extracting unique embedding for each person and comparing them or training model on face images like YoloFace and after that do the same. Secondly, How many images for each person are required for training? Is it better to extract faces from image and use them for training or use the original image?

Shrinkhal01 commented 8 months ago

i guess it might be possible to detet it using a pretrained with some modifications in the tensorflow project i have made in my repo:"https://github.com/Shrinkhal01/-Real-time-Object-Detection-using-TensorFlow-and-OpenCV"

WongKinYiu commented 7 months ago

https://github.com/WongKinYiu/yolov9/blob/main/README.md#useful-links