Release Release v1.11.0 · sony/model_optimization

What's Changed

Structured pruning for Keras models: MCT now employs structured and hardware-aware pruning. This pruning technique is designed to compress models for specific hardware architectures, taking into account the target platform's "Single Instruction, Multiple Data" (SIMD) capabilities.
- Additional details can be found here.
- Run a tutorial on Google Colab!
Learned Step Size Quantization (LSQ) implementation for QAT. To understand how to use LSQ, please refer to our API documentation here.

New tutorials were added! Nanodet-Plus, EfficientDet, and more. These tutorials and more can be found here.
Support for new NN framework versions was added (Tensorflow v2.14 and Pytorch v2.1).
Hessian scores used as sensitivity importance scores in mixed-precision, GPTQ, and pruning now support Hessian scoring w.r.t model's weights (in addition to previously supported Hessian w.r.t model's activations).
Added support for external regularization factor in GPTQ. Please refer to the API for Keras and Pytorch usage.
Custom layers in Keras, previously unsupported, are now skipped during quantization.

Names of Hessian-related variables and methods have been revised:
- GPTQHessianWeightsConfig Changes:
  - The class GPTQHessianWeightsConfig is renamed GPTQHessianScoresConfig.
  - The parameter norm_weights is renamed norm_scores.
  - New API can be found here.
- MixedPrecisionQuantizationConfigV2 Changes:
  - The parameter use_grad_based_weights is renamed use_hessian_based_scores.
  - The parameter norm_weights is renamed norm_scores.
  - New API can be found here.
Exporter changes: New QuantizationFormat 'MCTQ' exports models with mct-quantizers modules. Also, TPC should not be passed during export; instead, a QuantizationFormat is passed directly. For more details and updated usage examples, please see here.
The output replacement mechanism has been eliminated from the Hessian computation. As a result, models with specific layer outputs, such as argmax, are now incompatible with the Hessian scoring metric in features like GPTQ and mixed-precision. So, Hessian scoring needs to be deactivated when using these features.

Fixed a permission error during TensorFlow model export on Windows systems. #865 by @jgerityneurala.
Fixed an issue with pickling torch models. [#841].
Fixed an issue with systems operating with multiple CUDA devices. [#613].
Fixed the unsupported NMS layer issue in mixed precision scenarios. [#844]
Fixed an issue with PyTorch reshape substitute. [#799].
Fixed an issue finalizing graph configuration following mixed-precision operations with mixed TPC. [#820].
Tackled numeric problems in mixed precision caused by large values in the distance metric. Fixed by setting a threshold in the MP quantization configuration, ensuring that if a distance value exceeds this threshold, the metric is scaled down.
Fixed an issue with reused TensorFlow SeparableConv2D decomposition concerning their reuse group.
Fix bug in PyTorch BN folding into ConvTranspose2d with groups>1.

Welcome @jgerityneurala and @edenlum for their first contributions! PR #865, PR #873

Full Changelog: v1.10.0...v1.11.0