Open miaowang525 opened 2 years ago
Hi, thanks a lot for your interest.
The way to call the multiple GPUs to run the test-time optimization is similar to what we usually do in the multi-GPUs training (i.e. using the torch.nn.DataParallel module).
And if you use multi-GPUs, you can increase the batch size, then you can accelerate the test-time optimization.
Hello @tangjiapeng Your work is great and i am very interested in your article, and I have some questions to ask you. I have five GPUs, how to call multiple GPUs to run code during training?