深度网络设计器

以交互方式创建和训练深度学习网络

以交互方式构建、可视化和训练深度学习网络。使用起始页加载适用于迁移学习的预训练图像分类网络。分析您的网络，检查您是否正确定义了架构，并在训练前检测问题。导入和可视化训练数据，指定训练选项，并使用训练进度动画图跟踪网络训练。生成代码以重新创建网络构造和训练，并将经过训练的网络导出到 Simulink^®。

此流程图显示在深度网络设计器中构建和训练深度学习模型的常见工作流。您可以在深度网络设计器中训练您的网络，或通过命令行导出未经训练的网络来进行训练。

Deep learning workflow. Step 1. Design network. Step 2. Import data. Step 3. Select training options. Step 4. Train network. Step 5. Export network.

App

深度网络设计器

设计、可视化和训练深度学习网络

函数

`trainingOptions`	Options for training deep learning neural network
`trainNetwork`	训练神经网络
`trainnet`	Train deep learning neural network （自 R2023b 起）

主题

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。
Train Networks Using Deep Network Designer
Interactively train deep learning networks in Deep Network Designer.
Import Data into Deep Network Designer
Import and visualize data in Deep Network Designer.
Import Custom Layer into Deep Network Designer
This example shows how to import a custom classification output layer with the sum of squares error (SSE) loss and add it to a pretrained network in Deep Network Designer.
Generate MATLAB Code from Deep Network Designer
Generate MATLAB^® code to recreate designing and training a network in Deep Network Designer.
Generate Experiment Using Deep Network Designer
Use Experiment Manager to tune the hyperparameters of a network trained in Deep Network Designer.
View Autogenerated Custom Layers Using Deep Network Designer
This example shows how to import a pretrained TensorFlow™ network and view the autogenerated layers in Deep Network Designer.