Main Content

内置训练

使用内置训练函数训练深度学习网络

定义网络架构后,您可以使用 trainingOptions 函数定义训练参数。然后,您可以使用 trainnet 函数训练网络。使用经过训练的网络预测类标签或数值响应。

App

深度网络设计器设计和可视化深度学习网络

函数

全部展开

dlnetworkDeep learning neural network (自 R2019b 起)
trainingOptionsOptions for training deep learning neural network
trainnetTrain deep learning neural network (自 R2023b 起)
TrainingInfoNeural network training information (自 R2023b 起)
showShow training information plot (自 R2023b 起)
closeClose training information plot (自 R2023b 起)
accuracyMetricDeep learning accuracy metric (自 R2023b 起)
aucMetricDeep learning area under ROC curve (AUC) metric (自 R2023b 起)
fScoreMetricDeep learning F-score metric (自 R2023b 起)
precisionMetricDeep learning precision metric (自 R2023b 起)
recallMetricDeep learning recall metric (自 R2023b 起)
rmseMetricDeep learning root mean squared error metric (自 R2023b 起)
predictCompute deep learning network output for inference (自 R2019b 起)
minibatchpredictMini-batched neural network prediction (自 R2024a 起)
scores2labelConvert prediction scores to labels (自 R2024a 起)
confusionchartCreate confusion matrix chart for classification problem
sortClassesSort classes of confusion matrix chart
classifyAndUpdateState(Not recommended) Classify data using a trained recurrent neural network and update the network state

主题