Closed wangjiongw closed 1 year ago
Also have same problem.
I got the same problem as well when I reimplement the algorithm. The training speed is really slow and the performance is really bad.
Does anyone have a solution?
In this repo, I didn't find an available solution. But there is an re-implementation of MvP in Mocap (https://github.com/openxrlab/xrmocap), batch size larger than 1 is okay in that repo.
please refer to https://github.com/openxrlab/xrmocap for improved implementation
When I run the validation code with given pretrained checkpoint on Panoptic dataset, I found that there is something wrong with batch size larger than 1. For example, When batch size=1, the precision can be reproduced.![image](https://user-images.githubusercontent.com/29309804/177721828-09750464-a925-4b64-b31a-73ef8850b44f.png)
When batch size=2, it seems that the model fails to predict correctly.![image](https://user-images.githubusercontent.com/29309804/177722042-6bda32a8-a064-444c-90ab-401428b60c4a.png)
Does anyone get the similar problem? Or can you please give some advice about the reason of this problem? thx!