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

move Keras qat activation quantizers to trainable infrastructure #1240

Merged
merged 4 commits into from
Oct 14, 2024
Merged

move Keras qat activation quantizers to trainable infrastructure #1240

merged 4 commits into from
Oct 14, 2024

Conversation

reuvenperetz
Copy link
Collaborator

Pull Request Description:

Move STE and LSQ activation quantizers in Keras from QAT to the new trainable infrastructure module.
Add flag 'freeze_quantization_params' to align them with pytorch quantizers (even though this flag is meaningless in Keras).
Rename Trainable QAT quantizer to be Weight Trainable quantizer.

Checklist before requesting a review:

  • I set the appropriate labels on the pull request.
  • I have added/updated the release note draft (if necessary).
  • I have updated the documentation to reflect my changes (if necessary).
  • All function and files are well documented.
  • All function and classes have type hints.
  • There is a licenses in all file.
  • The function and variable names are informative.
  • I have checked for code duplications.
  • I have added new unittest (if necessary).

@ofirgo ofirgo removed the request for review from irenaby October 14, 2024 06:05
ofirgo
ofirgo approved these changes Oct 14, 2024
View reviewed changes
Copy link
Collaborator

@ofirgo ofirgo left a comment

Choose a reason for hiding this comment

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

Approved with few minor comments

...ompression_toolkit/trainable_infrastructure/keras/activation_quantizers/lsq/symmetric_lsq.py Outdated Show resolved Hide resolved
..._compression_toolkit/trainable_infrastructure/keras/activation_quantizers/lsq/uniform_lsq.py Outdated Show resolved Hide resolved
...ompression_toolkit/trainable_infrastructure/keras/activation_quantizers/ste/symmetric_ste.py Outdated Show resolved Hide resolved
@reuvenperetz reuvenperetz merged commit fa2b3b7 into sony:main Oct 14, 2024
32 of 33 checks passed
@reuvenperetz reuvenperetz deleted the refactor-keras-activation-quantizers branch October 14, 2024 16:33
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ofirgo ofirgo ofirgo approved these changes

Assignees
No one assigned
Labels
auto:qat auto:tests auto:trainable_infrastructure
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@reuvenperetz @ofirgo