deep learning toolbox model quantization library -凯发k8网页登录

deep learning toolbox model quantization library

作者:

quantize and compress deep learning models

1.6k 次下载

更新时间 2023/12/13

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.

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 structural compression of models with and . both techniques reduce the sizes of deep neural networks by removing elements that have the smallest impact on inference accuracy.

please refer to the documentation here:

quantization workflow prerequisites can be found here:

if you have download or installation problems, please contact technical support -

additional resources

learn more about
quantization aware training (qat) with mobilenet-v2 (, )
overview video -

matlab 版本兼容性

创建方式 r2020a

兼容 r2020a 到 r2024a 的版本

平台兼容性

windows macos (apple 芯片) macos (intel) linux

类别

在和中查找有关 deep learning toolbox 的更多信息

community treasure hunt

find the treasures in matlab central and discover how the community can help you!

start hunting!

deep learning toolbox model quantization library -凯发k8网页登录