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.

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

Onnx gemm attributes #242

Merged
merged 4 commits into from
Apr 22, 2020

Conversation

kjulian3
Copy link
Collaborator

This pull request addresses #239 by adding support for the four Gemm attributes (transA, transB, alpha, and beta), as well as fixing an edge case for the Matmul function. These bugs were found using networks exported from PyTorch.

Copy link
Collaborator

@wu-haoze wu-haoze left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

maraboupy/MarabouNetworkONNX.py Show resolved Hide resolved
@kjulian3 kjulian3 merged commit 7448736 into NeuralNetworkVerification:master Apr 22, 2020
@kjulian3 kjulian3 deleted the onnx_gemm_trans branch April 22, 2020 20:02
AleksandarZeljic pushed a commit to AleksandarZeljic/Marabou that referenced this pull request Oct 9, 2020
* Handle more cases for Gemm and Matmul

* Remove extra space

Co-authored-by: Kyle Julian <kjulian3.stanford.edu>
matanost pushed a commit that referenced this pull request Nov 2, 2021
* Handle more cases for Gemm and Matmul

* Remove extra space

Co-authored-by: Kyle Julian <kjulian3.stanford.edu>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants