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apptrainNetwork
training 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
Export 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。To import any datastore, on the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。
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
。
选择培训选项后,单击训练网络Train。Deep Network Designer应用程序显示了训练进度的动画图。该图显示了小批量损失和准确性,验证损失和准确性以及有关培训进度的其他信息。该图有一个停止按钮在右上角。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。
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 thetrainNetwork
function 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, clickExportto export your trained network and results to the workspace.
Deep Network Designer does not support training using custom training loops. To train your network using a custom training loop, first export the network to the workspace and convert it to adlnetwork
object. You can then train the network using thedlnetwork
object and a custom training loop. For more information, seeTrain Network Using Custom Training Loop。
You can learn how to build and train your network using command line functions by clickingExport>生成培训代码and examining the generated live script. You can also use the generated script as a starting point to create deep learning experiments that sweep through a range of hyperparameter values or use Bayesian optimization to find optimal training options. For an example showing how to use实验经理to tune the hyperparameters of a network trained in Deep Network Designer, seeAdapt Code Generated in Deep Network Designer for Use in Experiment Manager。