when I use it, it aways say:
UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at …\c10/core/TensorImpl.h:1156.)
return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
how can I deal it?
I hope get your help
You can ignore it and update PyTorch (and torchvision) to the latest release, as the warning was unhelpful and was removed.
but updating libraries is scary what if it breaks all my code…
ok will do this monday I guess when I have more energy…
You could also ignore the warning, if you prefer to keep an older release.
Before changing your current setup, create a new conda/pip environment, install the latest libs there, and check your code. This would keep your current setup while you can test the updated one.
I know…not looking forward to it…thanks regardless