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)
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.