HodgeNet icon indicating copy to clipboard operation
HodgeNet copied to clipboard

code for prediction and visualization on segmentation output

Open amiltonwong opened this issue 4 years ago • 3 comments

Hi, @dmsm,

Could you also provide the code for prediction and visualization on segmentation output?

Thanks~

amiltonwong avatar Aug 10 '21 03:08 amiltonwong

Hi, @dmsm @amiltonwong , Can you retrain this code? I have been waiting in the line 78 of the hodgeautograd.py( ctx_eigenvectors.copy_(torch.from_numpy(reshaped_eigenvectors).to(device))) when run on the cpu; Did you meet this issure?

Thanks

Dengzhi-USTC avatar Aug 23 '21 12:08 Dengzhi-USTC

Hi, @dmsm @amiltonwong , Can you retrain this code? I have been waiting in the line 78 of the hodgeautograd.py( ctx_eigenvectors.copy_(torch.from_numpy(reshaped_eigenvectors).to(device))) when run on the cpu; Did you meet this issure?

Thanks

I solved this problem, need considerate the version of the torch.multiprocess. (Add the torch.multiprocessing.set_start_method('spawn', force=True) is ok)

Dengzhi-USTC avatar Aug 23 '21 13:08 Dengzhi-USTC

Have anyone tried to test and visualize the output of the model? I tried but not getting expected result .if anyone got then please give me some suggestion ..

ManjitKuma avatar May 27 '24 07:05 ManjitKuma