About the result of the model #5
Comments
Maybe, I think, there exists some differences between Tensorflow and PyTorch, since this reimplementation tried to be as same as the original version as possible. |
Thank you! |
Hi, @weigq |
@dmortem |
@weigq |
@dmortem |
@weigq And in the paper, I find "Camera coordinates" section which says "it is unrealistic to expect an algorithm to infer the 3d joint positions in an arbitrary coordinate space". So can we just regress the 3d coordinate without any processing on 2d coordinates except zero centering? |
If I understand correctly, i) the camera coordinates mean centering the pose ii) the normalization ((x- mean) / std) is a trick to boost the performance of model. There is something interesting, the paper said training without normalization can influence the performance and i have tried their tf version, the results without normalization is worse indeed. But i tried in this pytorch version, normalization dose not have great influence on the performance. |
Thank you for your explanation. So besides zero center, do I need to center the pose if I use my own 2d coordinate? The paper says "zero center the 3d poses around the hip joint". I wonder whether I need to do both "centering pose" and "normalization" on 3d poses, and only do "normalization" on 2d poses? |
Same as the original paper: |
Thanks for your kindness and patience! |
By the way, would you provide the codes for converting the original 3d poses in h36m to the centered ones? |
@dmortem would you be able to share the stat.pth.tar file please |
Hi, in case you still need stat.pth.tar file. It is here https://drive.google.com/drive/folders/1h4S3vmtjso_rxP6_Lfg6a1ue7pJMuGp9. Hope it helps. |
Hi,
Thanks for your codes. I wonder why the results of "original version" are different from the paper and the pytorch version is a little better than the paper?
Thanks a lot!
The text was updated successfully, but these errors were encountered: