Dafei Qin

I may encounter a similar problem here: ``` python from torch.utils.dlpack import to_dlpack from torch.utils.dlpack import from_dlpack from torch_sparse import spmm, transpose import cupy import torch class deformation_gradient(torch.autograd.Function): @staticmethod def...

> > ``` > > torch.cuda.set_device(device) > > ``` > > This addition code helps me training EG3D on 2080TIx8 which only has 11019MB memory each GPU, thanks a lot!...