Julieta Martinez

Hello @talenz and @lewin4, I have managed to reproduce the issue that you are reporting. I apologize. Since we developed this code on machines with distributed training with horovod, we...

Fixed by https://github.com/una-dinosauria/permute-quantize-finetune/pull/2. Cheers,

I've also added a docker image to make it easier to reproduce our results: https://github.com/una-dinosauria/permute-quantize-finetune/pull/3

Hi @RuipengZhang118, The file contains the Euler angle representation of a kinematic tree that represents the human body. With these transformations and a list of bone lengths, you can represent...

As you can see in the code you linked to https://github.com/una-dinosauria/human-motion-prediction/blob/c9a2774fe59bb78c6ec6d04e15f2cb7243c4348c/src/translate.py#L216-L221 we are simply following previous work.

Hi @DK-Jang, >1. The dimension of the angles received by the fkl function is 99, the first dim 1,2 and 3 represents the translation of the root joint, the dim...

You're taking code from two different repos. In 3d-pose-baseline we use 3d joints, not 3d angles. The numbers of joints in 3d and in the kinematic tree don't necessarily have...

Hi Sadegh, > Somewhere in your paper, you mentioned that H3.6M has 54 independent joint angles in 3D space. Are these correspond to 18 joints? Not necessarily. Some joints have...

I cant' think of any reason right now. Probably avoiding the first few frames since they tend to be people in T-pose.

@YongyiTang92 Regarding the error in dimensions selected, @Seleucia was kind enough to submit [a PR](https://github.com/una-dinosauria/human-motion-prediction/pull/17) that fixes this issue. If this is another problem with the code, could you please...