Apply Prune function on CNN

Question

frederic feresin 2019-1-21

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440761-apply-prune-function-on-cnn

回答： Maksym Tymchenko 2023-7-21

when pruning is applied to Alexnet, ML returns: "Undefined function 'prune' for input arguments of type 'SeriesNetwork'!" could you please explain how to apply "prune" function to CNN?

2 个评论
显示无隐藏无

Shaw 2021-11-3

Did you solve this question?

frederic feresin 2021-11-3

在 MATLAB Online 中打开

no!

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Maksym Tymchenko 2023-7-21

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440761-apply-prune-function-on-cnn#answer_1276823

Hi @frederic feresin,

In MATLAB, you can compress deep neural networks by using the Deep Learning Model Quantization Library, which is a free Add-On to the Deep Learning Toolbox.

This library contains a set of different functions that allow you to compress your deep learning network.

You mentioned pruning, this is a type of structural compression where the least important weights in the network are discarded making the network smaller. The "prune" function that you mentioned only accepts "shallow neural networks" as input. That is the reason why it did not work on AlexNet. If you want to perform structural compression on a deep neural network like Alexnet, you can use either:

The taylorPrunableNetwork function which enables you to prune convolutional filters in network.
The compressNetworkUsingProjection function which uses a MathWorks patented algorithm to analyze the activations of each layer using principal component analysis and reduce the size of the weights using projection.

Both of these functions work only on dlnetwork objects, so you might need to convert your network to that form in order to use them. For an example of how to prune convolutional filters in a CNN see:

Prune Image Classification Network Using Taylor Scores