Deep Learning Toolbox Model Quantization Library

Quantize and Compress Deep Learning models

다운로드 수: 1.4K

업데이트 날짜: 2023/10/19

Deep Learning Toolbox Model Quantization Library enables quantization and compression of your deep learning models to reduce the memory footprint and computational requirements of your deep neural network.
Quantization to 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.
The library also supports pruning which reduces network size by removing network elements that have the smallest impact on inference accuracy.
An example of Quantization Aware Training (QAT) with MobileNet-v2 is described at this GitHub link. The full GitHub repository can be found at this link.
Quantization Workflow Prerequisites can be found here:
If you have download or installation problems, please contact Technical Support -
MATLAB 릴리스 호환 정보
개발 환경: R2020a
R2020a에서 R2023b까지의 릴리스와 호환
플랫폼 호환성
Windows macOS (Apple silicon) macOS (Intel) Linux
Help CenterMATLAB Answers에서 Deep Learning Toolbox에 대해 자세히 알아보기

Community Treasure Hunt

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

Start Hunting!