mks0601 / NeuralAnnot_RELEASE

3D Pseudo-GTs of "NeuralAnnot: Neural Annotator for 3D Human Mesh Training Sets", CVPRW 2022 Oral.
168 stars 11 forks source link

smplx shape dimension is 16 not 10 #18

Closed Gaozhongpai closed 10 months ago

Gaozhongpai commented 10 months ago

Hi Gyeongsik,

I ran the demo_smplx.py and it failed because the shape size in smplx model is 16 while the data from the json file is 10. I added the following code to solve the issue:

shape = torch.cat([shape, torch.zeros((1, 6))], dim=-1)

Is this inconsistency caused by a different version of smplx repository?

mks0601 commented 10 months ago

Hi, sorry for the late reply. Maybe you're right, or you can explicitly set num_betas=10 when initializing smplx layer.