search

IBM / UQ360

Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you estimate, communicate and use uncertainty in machine learning model predictions.
https://uq360.res.ibm.com/
Apache License 2.0
257 stars 61 forks source link

Working GPU Example for demo_bnn_classification.ipynb #28

Open janfelixklein opened 2 years ago

janfelixklein commented 2 years ago

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

pronics2004 commented 2 years ago

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