网络压缩快速入门
学习 Deep Learning Toolbox™ Model Compression Library 的基础知识
将 Deep Learning Toolbox 与 Deep Learning Toolbox Model Compression Library 支持包结合使用，以减少深度神经网络的内存占用和计算要求：
使用一阶泰勒逼近从卷积层中对滤波器进行剪枝。
通过对层激活执行主成分分析 (PCA) 来对层进行投影。
将层的权重、偏置和激活量化为精度降低的缩放整数数据类型。
然后，您可以从压缩后的网络生成代码，并将其部署到所需的硬件。
主题
- Reduce Memory Footprint of Deep Neural Networks
Learn about neural network compression techniques, including pruning, projection, and quantization.
精选示例
Analyze and Compress 1-D Convolutional Neural Network
Analyze 1-D convolutional network for compression and compress it using Taylor pruning and projection.
Export Quantized Networks to Simulink and Generate Code
Export a quantized neural network to Simulink and generate code from the exported model.
Parameter Pruning and Quantization of Image Classification Network
Use parameter pruning and quantization to reduce network size.
