You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The prediction of YOLOv3 usually a rectangle and I see that you use transforms method to resize the image before put it into HRNet. It stretching the image and make pose estimation network performs badly.
I try to make YOLOv3 prediction regions have the same h/w ratio as the input of HRNet. For example, HRNet requires image_resolution (256, 256),but YOLOv3 gives a rectangle region. What we should do is calculate the center of YOLO prediction region and expand it as a square.
In SimpleHRNet._predict_single I modify it by adding:
Adapt detection bounding boxes to match HRNet input aspect ratio (as suggested by xtyDoge in issue #14). Huge accuracy improvement in the multiperson setting.
The prediction of YOLOv3 usually a rectangle and I see that you use transforms method to resize the image before put it into HRNet. It stretching the image and make pose estimation network performs badly.
I try to make YOLOv3 prediction regions have the same h/w ratio as the input of HRNet. For example, HRNet requires image_resolution (256, 256),but YOLOv3 gives a rectangle region. What we should do is calculate the center of YOLO prediction region and expand it as a square.
In
SimpleHRNet._predict_single
I modify it by adding:And it works on pose_hrnet_w32_256x256 with mpii annotation.
Maybe you can add it on your proj :D
The text was updated successfully, but these errors were encountered: