In regress_kp(bctch_list) from celeba_wild.py, there are only 2 keys 'det_keypoints' and 'keypoints'.
Should I add "'eye_distance': batch['eye_distance'].cpu()" to line 93 of model.py which is originally "out_batch = {'keypoints': batch['keypoints'].cpu(), 'det_keypoints': kp.cpu()}"?
Yes. You will need eye_distance during inference. I think it can also be inferred from the GT keypoints, but I seemed to forget to modify the dataset-specific testing code.
In regress_kp(bctch_list) from celeba_wild.py, there are only 2 keys 'det_keypoints' and 'keypoints'. Should I add "'eye_distance': batch['eye_distance'].cpu()" to line 93 of model.py which is originally "out_batch = {'keypoints': batch['keypoints'].cpu(), 'det_keypoints': kp.cpu()}"?![QQ_1720710315921](https://github.com/xingzhehe/AutoLink-Self-supervised-Learning-of-Human-Skeletons-and-Object-Outlines-by-Linking-Keypoints/assets/54067417/a2d4db17-2ed3-4da4-b077-9e1916cc14ab)