sony / model_optimization

Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers advanced quantization and compression tools for deploying state-of-the-art neural networks.
https://sony.github.io/model_optimization/
Apache License 2.0
331 stars 53 forks source link

Gradual activation quantization in Keras #1244

Closed reuvenperetz closed 4 weeks ago

reuvenperetz commented 1 month ago

Pull Request Description:

Add support for gradual activation quantization in Keras. This mainly converts torch implementation of gradual activation quantization to a common implementation. In addition, pytests tests were added to keras (similar to current pytorch tests).

Checklist before requesting a review: