Lotayou / everybody_dance_now_pytorch

A PyTorch Implementation of "Everybody Dance Now" from Berkeley AI lab.
GNU Affero General Public License v3.0
279 stars 72 forks source link

Not have NVIDIA card #6

Closed AbdulBariKhan closed 5 years ago

AbdulBariKhan commented 5 years ago

Can this code run without using CUDA.

Lotayou commented 5 years ago

It can, but will take you ages to train the network... If you insist, just deploy the model on CPU device with torch.device('cpu')

AbdulBariKhan commented 5 years ago

Will it work? And where to deploy with torch.device('cpu')

AbdulBariKhan commented 5 years ago

Please let me know.