Question about running about atlasnet

[ThibaultGROUEIX]

Hi @tang-y-q

I see sh: 1: tmux: not found
I suggest to install tmux.

sudo apt-get install tmux

Best regards
Thibault

[tang-y-q]

Hi @tang-y-q

I see sh: 1: tmux: not found I suggest to install tmux.

sudo apt-get install tmux

Best regards Thibault

Hi Thibault
Thank you very much for your reply. However, some problems occurred when I used your pretrained parameters for testing.
When I use the atlasnet_autoencoder_1_sphere trained_models, it can run normally. However, when I use atlasnet_autoencoder_25_squares trained_models , an error is reported as follows:

THCudaCheck FAIL file=/pytorch/torch/csrc/cuda/Module.cpp line=59 error=10 : invalid device ordinal
Traceback (most recent call last):
File "/home/yukon/AtlasNet-master/train.py", line 15, in
torch.cuda.set_device(opt.multi_gpu[0])
File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/torch/cuda/init.py", line 292, in set_device
torch._C._cuda_setDevice(device)
RuntimeError: cuda runtime error (10) : invalid device ordinal at /pytorch/torch/csrc/cuda/Module.cpp:59

I found many methods on the Internet, but none of them can solve this problem.It is said on the Internet that Pytorch will save the video card information when saving the model. When reloading, it will report an error if it finds that the video card is not the same.But I still can't solve this problem.
Could you please tell me how to modify the code to make it work properly？

Best regards Yukon