Jiong WANG

I met the same problem. And fortunately there is no missing files, but some naming errors. You can find that the proposed model is exactly defined in 'oneshot/onemodel_sg-one.py'. I solved...

Maybe You should change the string in oneshot/__init__.py to the proposed model file; and input the architecture name to arg_parser

> > When I prepare to run experiments on Human 3.6M dataset, I found that the **getitem** function calls the function from the class it inheritates, which is JointDataset, but...

> 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.