Bug with n_joints in train.py

[Samleo8]

learnable-triangulation-pytorch/train.py

Line 194 in 5220551

n_joints = keypoints_3d_pred[0].shape[1]

I believe this is an error, because keypoints_3d_pred has shape [<batch_size>, <num_keypoints>, 3].

Therefore, this should be changed to either
n_joints = keypoints_3d_pred.shape[1] or n_joints = keypoints_3d_pred[0].shape[0].

[uyoung-jeong]

It seems that n_joints is only used in 1-view case. As long as we don't run it in 1-view setup, it would cause no trouble. By the way, I was surprised that I didn't even notice this problem while I ran the script dozens of times. Thank you!

[Samleo8]

Unfortunately even if you don't intend to run it with the 1-view setup, what I found is that sometimes if the CMU dataset has missing BBOX data for certain cameras/frames. If you have 3 cameras/views but 2 of them have invalid BBOXes, the algorithm will take that particular batch as a 1-view case.

[karfly]

Oh, missed this issue. Thank you @Samleo8 and @uyoung-jeong, fixed that here: acee6d2