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

Support for unsqueeze ONNX opset 1 #1645

Closed
antimora opened this issue Apr 16, 2024 · 0 comments · Fixed by #1661
Closed

Support for unsqueeze ONNX opset 1 #1645

antimora opened this issue Apr 16, 2024 · 0 comments · Fixed by #1661
Assignees
@antimora
Labels
bug Something isn't working onnx

Comments

@antimora
Copy link
Collaborator

Describe the bug

Current ONNX implementation does not support Unsqueeze OpSet 1 where only one input is expected and axes is passed via attributes: https://onnx.ai/onnx/operators/onnx__Unsqueeze.html#unsqueeze-1

To Reproduce

  1. Follow the steps to download ONNX file from this issue: Only tensor input is valid when converting ONNX model #1593
  2. Run: [burn-import]% cr ./clip_image_model_vitb32_batchsize1.onnx ./out

Expected behavior

Screenshots

image image
@antimora antimora added bug Something isn't working onnx labels Apr 16, 2024
@antimora antimora self-assigned this Apr 18, 2024
@antimora antimora mentioned this issue Apr 18, 2024
Merged
2 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@antimora antimora

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

Successfully merging a pull request may close this issue.

Fix bug 1645 (Unsqueeze OpSet 11) antimora/burn
1 participant
@antimora