投影
使用主成分分析 (PCA) 对网络层进行投影；减少可学习参数的数量
对层进行投影，先使用代表训练数据的数据集对层激活执行主成分分析 (PCA)，然后对层的可学习参数应用线性投影。当您使用无库的 C/C++ 代码生成将网络部署到嵌入式硬件时，投影的深度神经网络的前向传导通常会更快。
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
compressNetworkUsingProjection | Compress neural network using projection (自 R2022b 起) |
neuronPCA | Principal component analysis of neuron activations (自 R2022b 起) |
unpackProjectedLayers | Unpack projected layers of neural network (自 R2023b 起) |
ProjectedLayer | Compressed neural network layer using projection (自 R2023b 起) |
gruProjectedLayer | Gated recurrent unit (GRU) projected layer for recurrent neural network (RNN) (自 R2023b 起) |
lstmProjectedLayer | Long short-term memory (LSTM) projected layer for recurrent neural network (RNN) (自 R2022b 起) |
主题
- Compress Neural Network Using Projection
Compress a neural network using projection and principal component analysis (PCA).
- Train Smaller Neural Network Using Knowledge Distillation
Reduce the memory footprint of a deep neural network using knowledge distillation. (自 R2023b 起)
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.
Evaluate Code Generation Inference Time of Compressed Deep Neural Network
Compare the inference time of a compressed deep neural network for battery state of charge estimation.
