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

Add DepthwiseConv2D to Conv2D substitution #826

Merged
merged 6 commits into from
Oct 17, 2023

Conversation

Idan-BenAmi
Copy link
Collaborator

Substitution for Keras DepthwiseConv2D which isn't handled correctly once depth_multiplier is not 1. The substitution will replaced it with Conv2D and "groups" parameters equal to number of output channels.

@reuvenperetz
Copy link
Collaborator

General comment:
Add comments to the substitution (especially with the shapes thing).
I would also add a simple test with a single layer, to see how it's being transformed.

@Idan-BenAmi Idan-BenAmi merged commit 827b177 into sony:main Oct 17, 2023
22 checks passed
reuvenperetz pushed a commit to reuvenperetz/model_optimization that referenced this pull request Oct 22, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants