search

kfzyqin / Implementation-MolGAN-PyTorch

PyTorch implementation of MolGAN: MolGAN: An implicit generative model for small molecular graphs.
53 stars 9 forks source link

RuntimeError: CUDA out of memory #7

Open shikhar2402 opened 2 years ago

shikhar2402 commented 2 years ago

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

kfzyqin commented 2 years ago

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