weigq

@mohomran Maybe you forgot to add the submodules into .git

@wangsen1312 You can refer to my pull request, I fixed it.

@SunTongtongtong You can directly clone from my forked repo by `git clone --recursive https://github.com/weigq/neural_body_fitting`. The author just add the sbmodule info into `.gitsubmodules`, while the true way to add a...

@abhikhanna30 is there any more info?

This is due to python version, the codes only tested in pytho2.7, there are some problems in python3

@alecda573 - Why the number of 3D samples is different with that of 2D samples? It is because one single video (I am not sure it is one or more,...

@alecda573 - Yes. - If I understand correctly, you can calculate the Euler angles representation from GT 3D pose.

please refer to https://github.com/weigq/3d_pose_baseline_pytorch/issues/26

same as the original repo, the 2d pose is obtained from the `1000x1000` image, which means that the unnormalized 2d pose lies in `1000x1000`.

I do not know the details how they generate the 2d detections, however, i think, they crop the image when running the staked hourglass. And the final 2d pose they...