search

Walter0807 / MotionBERT

[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"
Apache License 2.0
1.02k stars 123 forks source link

About evaluate function during training #48

Closed tszhang97 closed 1 year ago

tszhang97 commented 1 year ago

Hi, I use the training code and find something wrong. https://github.com/Walter0807/MotionBERT/blob/ec48976542ba746fd1b48054502be03888fbab86/train.py#LL340C89-L340C89 The test dataloader include AMASS, and in dataset_motion_3d.py, 2d input use motion_file['data_input'] which is None when generating AMASS testset. So, how to use AMASS testset or just use H3.6M testset？ Looking forward to your reply, thx! image image

Walter0807 commented 1 year ago

Hi, we use AMASS for pretraining, and no AMASS data is used for testing. The test loader should contain H36M motion only.