构建深度神经网络

使用 MATLAB^® 代码或以交互方式使用深度网络设计器为图像数据构建神经网络

通过从头开始定义网络架构，为图像分类和回归等任务创建新的深度网络。使用 MATLAB 或以交互方式使用深度网络设计器构建网络。

对于大多数任务，您可以使用内置层。如果没有您的任务所需的内置层，则可以定义您自己的自定义层。您可以定义具有可学习参数和状态参数的自定义层。定义自定义层后，您可以检查该层是否有效，是否与 GPU 兼容，以及是否输出正确定义的梯度。要查看支持的层的列表，请参阅深度学习层列表。

对于无法指定为由层组成的网络的模型，可以将模型定义为函数。要了解详细信息，请参阅定义自定义训练循环、损失函数和网络。

App

设计和可视化深度学习网络

`imageInputLayer`	Image input layer
`image3dInputLayer`	3-D image input layer

`convolution2dLayer`	2-D convolutional layer
`convolution3dLayer`	3-D convolutional layer
`groupedConvolution2dLayer`	2-D grouped convolutional layer
`transposedConv2dLayer`	Transposed 2-D convolution layer
`transposedConv3dLayer`	Transposed 3-D convolution layer
`fullyConnectedLayer`	Fully connected layer

`selfAttentionLayer`	Self-attention layer (自 R2023a 起)
`attentionLayer`	Dot-product attention layer (自 R2024a 起)
`positionEmbeddingLayer`	Position embedding layer (自 R2023b 起)
`sinusoidalPositionEncodingLayer`	Sinusoidal position encoding layer (自 R2023b 起)
`embeddingConcatenationLayer`	Embedding concatenation layer (自 R2023b 起)
`indexing1dLayer`	1-D indexing layer (自 R2023b 起)

neuralODELayer Neural ODE layer (自 R2023b 起)

`reluLayer`	修正线性单元 (ReLU) 层
`leakyReluLayer`	Leaky Rectified Linear Unit (ReLU) layer
`clippedReluLayer`	Clipped Rectified Linear Unit (ReLU) layer
`eluLayer`	Exponential linear unit (ELU) layer
`tanhLayer`	双曲正切 (tanh) 层
`swishLayer`	Swish layer (自 R2021a 起)
`geluLayer`	Gaussian error linear unit (GELU) layer (自 R2022b 起)
`sigmoidLayer`	Sigmoid layer (自 R2020b 起)
`softmaxLayer`	Softmax 层
`functionLayer`	Function layer (自 R2021b 起)

`batchNormalizationLayer`	Batch normalization layer
`groupNormalizationLayer`	Group normalization layer (自 R2020b 起)
`instanceNormalizationLayer`	Instance normalization layer (自 R2021a 起)
`layerNormalizationLayer`	Layer normalization layer (自 R2021a 起)
`crossChannelNormalizationLayer`	Channel-wise local response normalization layer

`averagePooling2dLayer`	Average pooling layer
`averagePooling3dLayer`	3-D average pooling layer
`adaptiveAveragePooling2dLayer`	Adaptive average pooling 2-D layer (自 R2024a 起)
`globalAveragePooling2dLayer`	2-D global average pooling layer (自 R2019b 起)
`globalAveragePooling3dLayer`	3-D global average pooling layer (自 R2019b 起)
`globalMaxPooling2dLayer`	Global max pooling layer (自 R2020a 起)
`globalMaxPooling3dLayer`	3-D global max pooling layer (自 R2020a 起)
`maxPooling2dLayer`	Max pooling layer
`maxPooling3dLayer`	3-D max pooling layer
`maxUnpooling2dLayer`	Max unpooling layer

`dlnetwork`	Deep learning neural network (自 R2019b 起)
`imagePretrainedNetwork`	Pretrained neural network for images (自 R2024a 起)
`resnetNetwork`	2-D residual neural network (自 R2024a 起)
`resnet3dNetwork`	3-D residual neural network (自 R2024a 起)
`addLayers`	Add layers to neural network
`removeLayers`	Remove layers from neural network
`replaceLayer`	Replace layer in neural network
`connectLayers`	Connect layers in neural network
`disconnectLayers`	Disconnect layers in neural network
`addInputLayer`	Add input layer to network (自 R2022b 起)
`expandLayers`	Expand network layers (自 R2024a 起)
`groupLayers`	Group layers into network layers (自 R2024a 起)
`initialize`	Initialize learnable and state parameters of a `dlnetwork` (自 R2021a 起)
`networkDataLayout`	Deep learning network data layout for learnable parameter initialization (自 R2022b 起)
`setL2Factor`	Set L₂ regularization factor of layer learnable parameter
`getL2Factor`	Get L₂ regularization factor of layer learnable parameter
`setLearnRateFactor`	Set learn rate factor of layer learnable parameter
`getLearnRateFactor`	Get learn rate factor of layer learnable parameter

`plot`	绘制神经网络架构
`summary`	打印网络摘要 (自 R2022b 起)
`analyzeNetwork`	Analyze deep learning network architecture
`checkLayer`	Check validity of custom or function layer
`isequal`	Check equality of neural networks (自 R2021a 起)
`isequaln`	Check equality of neural networks ignoring `NaN` values (自 R2021a 起)

创建简单的深度学习神经网络以用于分类
此示例说明如何创建和训练简单的卷积神经网络来进行深度学习分类。
针对回归训练卷积神经网络
此示例说明如何训练卷积神经网络来预测手写数字的旋转角度。
深度学习层列表
探索 MATLAB 中的所有深度学习层。
使用深度网络设计器构建网络
在深度网络设计器中以交互方式构建和编辑深度学习网络。
在 MATLAB 中进行深度学习
通过使用卷积神经网络进行分类和回归来探索 MATLAB 的深度学习能力，包括预训练网络和迁移学习，以及在 GPU、CPU、集群和云上进行训练。
Deep Learning Tips and Tricks
Learn how to improve the accuracy of deep learning networks.
Data Sets for Deep Learning
Discover data sets for various deep learning tasks.
Multiple-Input and Multiple-Output Networks
Learn how to define and train deep learning networks with multiple inputs or multiple outputs.
Example Deep Learning Networks Architectures
This example shows how to define simple deep learning neural networks for classification and regression tasks.