UQ360 icon indicating copy to clipboard operation
UQ360 copied to clipboard

Working GPU Example for demo_bnn_classification.ipynb

Open janfelixklein opened this issue 2 years ago • 1 comments

Hallo guys!

I just wanted to try out your example as mentioned in header. However I get the error

"Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!"

when running the fit method of the BnnClassification. Have you tried this example on a GPU machine? When I set device = torch.device("cpu"), it runs smoothly.

I have taken a closer look in your implementions and found several places, where tensors are created without having the device in mind.

Best regards

JFK

janfelixklein avatar Nov 04 '22 14:11 janfelixklein

Thanks @janfelixklein. We will follow up on this issue. Meanwhile, if you have a working fix, please feel free to submit a PR.

FYI: @SoumyaTGhosh

pronics2004 avatar Nov 04 '22 14:11 pronics2004