Open h310558606 opened 2 years ago
I got the same problem.
I believe the reason is that in sep_vqvae step, the final visulaization uses the ground truth root shift (because VQVAE in this step is not trained with the global velocity function; that is trained in the next step). The GT root does not begin from zero, making a shift upwards. So you could only see halfbody. We will enhance this soon.
Hello,Is this issue resolved now?I meet the same problem.
When I run 'python main.py --config configs/sep_vqvae.yaml --eval' using you pretrained model, I can only see the lower half body. [