amituofo1996

About training details

3

Hi, I'm xiaofeng. Can you add more details about training VPOSER, thank you

Hi, great work using VAE. I can't open your demo website.Could you rewrite the demo website link?

if you just change the suffix of the picture ,you will get this error in the command > ValueError: invalid PNG header you should change the picture through the professional...

Thanks

Hi, it is really a nice work. I want to get anxis-angle format result.Following is my code. with torch.no_grad(): pred_rotmat, pred_betas, pred_camera = model(norm_img.to(device)) pred_output = smpl(betas=pred_betas, body_pose=pred_rotmat[:,1:], global_orient=pred_rotmat[:,0].unsqueeze(1), pose2rot=False,return_full_pose=True)...

About Training Data Problem

2

Hi, Great work! When I prepare data and start trainning , one problem happen. (human_motion_prior) xiaofeng@xiaofeng-Precision-Tower-7910:/media/xiaofeng/E/code/human-motion-prior-main/human_motion_prior/train$ sh run_script.sh 1 tensorboard --logdir=logs/motion_prior/summaries Torch Version: 1.1.0 1 CUDAs available! Training with cuda...

input is one picture output is predicted motion I want to deal with this problem thanks

About can not reproduction

1

Thanks for offer good code! when I use your code and retrain, meet this issue.In your paper Table 4, PA-MPJPE=54.0, but I got 58.8, all trainning setting is same except...