剪枝

R2026b

通过对卷积层中最不重要的滤波器进行剪枝，减少神经网络中的可学习参数的数量

剪枝通过删除卷积层中最不重要的滤波器来减少神经网络中的可学习参数的数量。

如果可以使用 trainnet 函数训练网络，则使用 compressNetworkUsingTaylorPruning 函数对网络进行剪枝。如果无法使用 trainnet 函数训练网络，则改用 taylorPrunableNetwork 对象来创建自定义剪枝循环。

有关 Deep Learning Toolbox™ Model Compression Library 中提供的压缩技术的详细概述，请参阅Reduce Memory Footprint of Deep Neural Networks。

函数

compressNetworkUsingTaylorPruning Compress neural network using Taylor pruning (自 R2026a 起)

`taylorPrunableNetwork`	Neural network suitable for compression using Taylor pruning (自 R2022a 起)
`forward`	计算深度学习网络输出以进行训练
`predict`	计算深度学习网络输出以进行推断
`updatePrunables`	Remove filters from prunable layers based on importance scores (自 R2022a 起)
`updateScore`	Compute and accumulate Taylor-based importance scores for pruning (自 R2022a 起)

Prune Neural Network with Memory Requirement
This example shows how to compress a neural network to a specific size using Taylor pruning. (自 R2026a 起)
Prune Neural Network with Accuracy Requirement
This example shows how to compress a neural network with a minimum accuracy requirement using Taylor pruning. (自 R2026a 起)
Prune Image Classification Network Using Taylor Scores
Reduce the size of a deep neural network using Taylor pruning.
Prune Filters in a Detection Network Using Taylor Scores
Reduce network size and increase inference speed by pruning convolutional filters in a you only look once (YOLO) v3 object detection network.
Prune and Quantize Convolutional Neural Network for Speech Recognition
Compress a convolutional neural network (CNN) to prepare it for deployment on an embedded system.
Parameter Pruning and Quantization of Image Classification Network
Use parameter pruning and quantization to reduce network size.

Compress a neural network to a specific size using Taylor pruning.

Compress a neural network with a minimum accuracy requirement using Taylor pruning.

Analyze 1-D convolutional network for compression and compress it using Taylor pruning and projection.