RuntimeError: Could not run 'torchvision::roi_align' with arguments from the 'CUDA' backend. #5

Open
opened 2026-01-29 21:35:52 +00:00 by claunia · 0 comments
Owner

Originally created by @lxy2017 on GitHub (Jun 21, 2021).

When I train the code, I get the following error

RuntimeError: Could not run 'torchvision::roi_align' with arguments from the 'CUDA' backend. 'torchvision::roi_align' is only available for these backends: [CPU, BackendSelect, Named, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradPrivateUse1, AutogradPrivateUse2, AutogradPrivateUse3, Tracer, Autocast, Batched, VmapMode].

image

Originally created by @lxy2017 on GitHub (Jun 21, 2021). When I train the code, I get the following error RuntimeError: Could not run 'torchvision::roi_align' with arguments from the 'CUDA' backend. 'torchvision::roi_align' is only available for these backends: [CPU, BackendSelect, Named, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradPrivateUse1, AutogradPrivateUse2, AutogradPrivateUse3, Tracer, Autocast, Batched, VmapMode]. ![image](https://user-images.githubusercontent.com/9693098/122701302-7de87d00-d27f-11eb-8376-77149695cc22.png)
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: TencentARC/GFPGAN#5