nachiket92/conv-social-pooling

Use cpu instead of gpu

Closed this issue · 1 comments

amirrezahjr commented

I don't have NVIDIA graphic installed on my system. I'm wondering if I can run this code with a limited dataset on CPU instead of GPU?

nachiket92 commented

You can run training on CPU if you set args['use_cuda'] to false in train.py. It will be much slower though.