自定义训练循环

使用自定义训练循环来训练深度学习网络

如果 trainingOptions 函数不提供任务所需的训练选项，或者自定义输出层不支持所需的损失函数，则您可以定义自定义训练循环。对于无法使用层图创建的网络，可以将自定义网络定义为函数。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。

函数

`dlnetwork`	Deep learning neural network (自 R2019b 起)
`trainingProgressMonitor`	Monitor and plot training progress for deep learning custom training loops (自 R2022b 起)
`minibatchqueue`	Create mini-batches for deep learning (自 R2020b 起)
`padsequences`	Pad or truncate sequence data to same length (自 R2021a 起)
`dlarray`	Deep learning array for customization (自 R2019b 起)
`dlgradient`	Compute gradients for custom training loops using automatic differentiation (自 R2019b 起)
`dlfeval`	Evaluate deep learning model for custom training loops (自 R2019b 起)

`crossentropy`	Cross-entropy loss for classification tasks (自 R2019b 起)
`l1loss`	L₁ loss for regression tasks (自 R2021b 起)
`l2loss`	L₂ loss for regression tasks (自 R2021b 起)
`huber`	Huber loss for regression tasks (自 R2021a 起)
`mse`	Half mean squared error (自 R2019b 起)
`ctc`	Connectionist temporal classification (CTC) loss for unaligned sequence classification (自 R2021a 起)

Train Network Using Custom Training Loop
This example shows how to train a network that classifies handwritten digits with a custom learning rate schedule.
Train Sequence Classification Network Using Custom Training Loop
This example shows how to train a network that classifies sequences with a custom learning rate schedule.
定义自定义训练循环、损失函数和网络
了解如何使用自动微分来定义和自定义深度学习训练循环、损失函数和网络。
Specify Training Options in Custom Training Loop
Learn how to specify common training options in a custom training loop.
Monitor Custom Training Loop Progress
Track and plot custom training loop progress.
Detect Issues During Deep Neural Network Training
This example shows how to automatically detect issues while training a deep neural network.