search

Mael-zys / T2M-GPT

(CVPR 2023) Pytorch implementation of “T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations”
https://mael-zys.github.io/T2M-GPT/
Apache License 2.0
574 stars 52 forks source link

training stuck #5

Closed qiqiApink closed 1 year ago

qiqiApink commented 1 year ago

When I tried to train vq_vae, the program was stuck on line 52 of train_vq.py which is for log printing. And I added "print(1)" after line 52, the "1" cannot be printed. Can you help me with some advice?

I checked again and found that the program was stuck on line 21 of evaluator_wrapper.py: checkpoint = torch.load(pjoin(opt.checkpoints_dir, opt.dataset_name, 'text_mot_match', 'model', 'finest.tar'), map_location=opt.device) How can I fix this?

fzlittlekid commented 1 year ago

I have encountered the same problem as you did, may I ask how did you solve it?

TiYife commented 10 months ago

How did you solve this problem？