Deep Learning Toolbox Model Compression Library

by bat365 Fixed Point Team
Optimize deep learning models with efficient compression techniques
3.8
(10)
2.3K Downloads
Updated 11 Dec 2024
Deep Learning Toolbox Model Compression Library enables compression of your deep learning models with pruning, projection, and quantization to reduce their memory footprint and computational requirements.
Pruning and projection are structural compression techniques that reduce the size of deep neural networks by removing learnables and filters that have the smallest impact on inference accuracy.
Quantization to 8-bit integers (INT8) is supported for CPUs, FPGAs, and NVIDIA GPUs, for supported layers. The library enables you to collect layer-level data on the weights, activations, and intermediate computations. Using this data, the library quantizes your model and provides metrics to validate the accuracy of the quantized network against the single precision baseline. The iterative workflow allows you to optimize the quantization strategy.
As of R2024b, you can export quantized networks to Simulink deep learning layer blocks for simulation and deployment to embedded systems.
Please refer to the documentation here: /help/deeplearning/quantization.html
Quantization Workflow Prerequisites can be found here:
/help/deeplearning/ug/quantization-workflow-prerequisites.html
If you have download or installation problems, please contact Technical Support - /contact_ts
Additional Resources
MATLAB Release Compatibility
Created with R2020a
Compatible with R2020a to R2025a
Platform Compatibility
Windows macOS (Apple silicon) macOS (Intel) Linux
Categories
Find more on Deep Learning Toolbox in Help Center and MATLAB Answers

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!