Vegetebird
commented
2 years ago The preprocessed code is referred to [1,2]. You can refer to their repo for more details.
[1] https://github.com/facebookresearch/VideoPose3D [2] https://github.com/vanoracai/Exploiting-Spatial-temporal-Relationships-for-3D-Pose-Estimation-via-Graph-Convolutional-Networks
Line 18: "assert poses_3d is None or poses_3d[key].shape[0] == poses_3d[key].shape[0]" What's the meaning of "poses_3d[key].shape[0] == poses_3d[key].shape[0]" here?
Line 22: "augment_vector = np.full(len(bounds - 1), False, dtype=bool)" What's the difference between "len(bounds - 1)" and "len(bounds)", i suppose they will get the same result.
I am looking forward to your kindly reply.