Skip to content

🐛Issue with brats_mri_segmentation bundle Torch_Tensorrt converting #1678

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Closed
apbose opened this issue Feb 16, 2023 · 1 comment · Fixed by #1695
Closed

🐛Issue with brats_mri_segmentation bundle Torch_Tensorrt converting #1678

apbose opened this issue Feb 16, 2023 · 1 comment · Fixed by #1695
Assignees
@apbose
Labels
bug Something isn't working

Comments

@apbose
Copy link
Collaborator

apbose commented Feb 16, 2023

Works in pytorch 22.10 docker but not in pytorch 23.01 docker.
See NVBugs for more details
@apbose apbose added the bug Something isn't working label Feb 16, 2023
@apbose apbose self-assigned this Feb 16, 2023
@apbose
Copy link
Collaborator Author

apbose commented Feb 17, 2023

The error comes in evaluator aten::slice.t(t[] l, int start, int end=9223372036854775807, int step=1) -> (t[]) where end is %self.convInit.conv.bias.27 : NoneType = prim::Constant() . It expects true in IValue isInt() unwrapping in unwraptoInt(), but the none type returns false.

@apbose apbose mentioned this issue Feb 22, 2023
Merged
7 tasks
@gs-olive gs-olive assigned apbose and bowang007 and unassigned bowang007 and apbose May 15, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@apbose apbose

Labels
bug Something isn't working
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Fixing aten::slice invalid schema and implementing aten::list evaluator pytorch/TensorRT
2 participants
@bowang007 @apbose