Skip to content
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

i am getting this issue while using the custom train weights but pretrained weights works fine #557

Open
Yogesh068 opened this issue Sep 7, 2023 · 3 comments
Open

i am getting this issue while using the custom train weights but pretrained weights works fine #557

Yogesh068 opened this issue Sep 7, 2023 · 3 comments

Comments

@Yogesh068
Copy link

Capture
@wenbingl
Copy link
Member

wenbingl commented Sep 8, 2023

As the error message suggested, you get a negative value in tensor shape on your inference.

BTW, how does this error relate to ort-extensions?

@FengYanNMG
Copy link

I am encountering a similar issue. Could you please advise me on how to resolve it? Thank you

@FengYanNMG
Copy link

FengYanNMG commented Dec 3, 2024 •
edited
Loading 

change yolo_e2e.py  add num_classes=1

add_ppp.yolo_detection(input_model_file, output_model_file, "jpg", onnx_opset=18,num_classes=1)
the num_classes is you nc

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@wenbingl @Yogesh068 @FengYanNMG