Closed leoozy closed 4 years ago
For most of the combinations, it should be straight-forward to run NST. I am not sure which combination you are running for.
If it can not be fit into the memory, try to do: (1) setting full loss to false here (2) reducing batch size (and also learning rate) (3) using mixed-precision training.
@leoozy , seems the problem gets solved? I am closing the issue now but feel free to reopen anytime.
Hi: Thank you for your code, I am trying to reimplement your benchmark. While running the nst loss, since the gram matrix is too large. Even if I use a 8 * P100(32GB) device, it is still out of memory. Could you please tell me whether you use some memory trick?Thank you