Implementation-MolGAN-PyTorch icon indicating copy to clipboard operation
Implementation-MolGAN-PyTorch copied to clipboard

Published 20 hours ago • verified publisher icon dagouchin

RuntimeError: CUDA out of memory

Open shikhar2402 opened this issue 3 years ago • 1 comments

I am facing this error while training the model after 21st epoch. RuntimeError: CUDA out of memory. Tried to allocate 2.00 MiB (GPU 0; 10.92 GiB total capacity; 9.98 GiB already allocated; 3.31 MiB free; 10.24 GiB reserved in total by PyTorch) @ZhenyueQin

shikhar2402 avatar Nov 25 '21 20:11 shikhar2402

I am not very sure about this error. Maybe try decreasing the batch size a little bit?

kfzyqin avatar Nov 26 '21 01:11 kfzyqin