Train Networks Using Deep Network Designer

TheDeep Network Designer应用程序使您可以构建和训练深层神经网络。深网设计师支持金宝apptrainNetworktraining using image data or datastore objects. You can also export your untrained network for training at the command line, for example, to train your network using custom training loops.

To train a network, follow these steps:

Create network
Import data
Select training options
火车网络
出口network

You can build a network interactively using Deep Network Designer, or import a network from the workspace. You can also select a pretrained network from the Deep Network Designer start page for transfer learning. For more information, seeBuild Networks with Deep Network Designer。

To train a deep learning model, you must have a suitable network and training data. To import image data from a folder containing a subfolder of images for each class, or from an成像object, on the数据tab, clickImport Data>导入图像数据。要导入任何数据存储数据tab, clickImport Data>Import Datastore。导入后，深网设计器将显示导入数据的预览，因此您可以在培训之前检查数据是否如预期。有关更多信息，请参阅Import Data into Deep Network Designer。

Select Training Options

拥有网络和数据后，下一步就是选择培训选项。在Trainingtab, clickTraining Options。If you do not know which training options to use, try training with the default settings and then adjusting them to suit your network and data. For example, try adjusting the initial learning rate, or train for longer by increasing the number of epochs. For information about techniques for improving the accuracy of deep learning networks, seeDeep Learning Tips and Tricks。For more information about the training options, see训练。

深网设计师中的培训选项对话框

Train Network

选择培训选项后，单击训练网络Train。深层网络设计师应用displays an animated plot of the training progress. The plot shows mini-batch loss and accuracy and additional information on the training progress. If you specified validation data, the plot also shows the validation loss and accuracy. The plot has a stop button在右上角。单击按钮停止训练并返回网络的当前状态。有关培训进度图的更多信息，请参阅Monitor Deep Learning Training Progress。

Training progress plot in Deep Network Designer

You can train a variety of networks using Deep Network Designer. For example, image classification or regression networks, sequence networks, numeric data networks, semantic segmentation networks, and image-to-image regression networks. In Deep Network Designer, you can train a network using thetrainNetworkfunction on any data that you can express as a datastore object. The following examples show how to build and train a network using Deep Network Designer.

培训完成后，Trainingtab, click出口to export your trained network and results to the workspace. To save the training progress plot as an image, click出口Training Plot。您可以通过单击使用命令行函数来学习如何构建和训练网络出口>生成培训代码and examining the generated live script.

Deep Network Designer不支持使用自定义培训金宝app循环的培训。要使用自定义培训循环训练您的网络，请首先将网络导出到工作区，然后将其转换为dlnetworkobject. You can then train the network using thedlnetworkobject and a custom training loop. For more information, seeTrain Network Using Custom Training Loop。

Next Steps

Once training is complete, click出口>创建实验在实验经理中创建深度学习实验。您可以使用实验管理器扫描一系列超参数值，也可以使用贝叶斯优化来找到最佳的培训选项。为了显示如何使用的示例实验经理to tune the hyperparameters of a network trained in Deep Network Designer, seeGenerate Experiment Using Deep Network Designer。