Why the keypoints whose coordinates are out of the input shape are reserved when generating the label heatmaps? about tf-cpn

[chenyilun95]

I think that's a bug we overlooked. But this kind of case may occur rarely and it won't hurt performance directly if it happens when testing.

[lilhope]

When computing loss, use the Tensor 'valid' multiple 'label', so the point out of boundary will not contribute to the loss, it won't hurt the performance.

[aBlueMouse]

I agree with the author's opinion, this situation is so few that it won't make harm, I just want to make sure whether you have some reasons. @chenyilun95
May you explain more details, I'm not quite catch what you mean, how to choose the 'valid label'? @lilhope
Thanks a lot!

[lilhope]

Sorry I did not explain it clearly. In practice, I notice that keypoints out of boundary was mainly come from the rotate augmentation. In dataset.py, line 118 ~ 119, the author use a valid variable to label the out of boundary keypoints as Invisible. In network.py, line 128 and line 132, the 'valid' act as the mask to make label[i,:]=0 where valid[i] < 0, so the label of the out of boundary keypoint was all zero.
So I think the out of boundary label won't harm the performance.

[aBlueMouse]

@lilhope I get it, thanks!