Questions about batch size larger than 1

[wangjiongw]

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.

When batch size=2, it seems that the model fails to predict correctly.

Does anyone get the similar problem? Or can you please give some advice about the reason of this problem? thx!

[axhiao]

Also have same problem.

[liqikai9]

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?

[wangjiongw]

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.

[twangnh]

please refer to https://github.com/openxrlab/xrmocap for improved implementation