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.
In Keras model, in case of a node with tuple/list of ints or dicts in the node's args, the MCT will not use these tuple/list as a const.
Pull Request Description:
Checklist before requesting a review: