Integriertes Training

Trainieren von Deep-Learning-Netzen mit integrierten Trainingsfunktionen

Nachdem Sie die Netzarchitektur definiert haben, können Sie die Trainingsparameter mit der Funktion trainingOptions festlegen. Sie können das Netz dann mit der Funktion trainnet trainieren. Verwenden Sie das trainierte Netz, um Klassenbezeichnungen oder numerische Antworten vorherzusagen.

Apps

Deep Network Designer

Entwurf und Visualisierung von Deep-Learning-Netzen

Funktionen

alle erweitern

Training

`dlnetwork`	Deep learning neural network (Seit R2019b)
`trainingOptions`	Options for training deep learning neural network
`trainnet`	Train deep learning neural network (Seit R2023b)
`TrainingInfo`	Neural network training information (Seit R2023b)
`show`	Show training information plot (Seit R2023b)
`close`	Close training information plot (Seit R2023b)

Metriken

`accuracyMetric`	Deep learning accuracy metric (Seit R2023b)
`aucMetric`	Deep learning area under ROC curve (AUC) metric (Seit R2023b)
`fScoreMetric`	Deep learning F-score metric (Seit R2023b)
`precisionMetric`	Deep learning precision metric (Seit R2023b)
`recallMetric`	Deep learning recall metric (Seit R2023b)
`rmseMetric`	Deep learning root mean squared error metric (Seit R2023b)

Vorhersage

`predict`	Compute deep learning network output for inference (Seit R2019b)
`minibatchpredict`	Mini-batched neural network prediction (Seit R2024a)
`scores2label`	Convert prediction scores to labels (Seit R2024a)
`confusionchart`	Create confusion matrix chart for classification problem
`sortClasses`	Sort classes of confusion matrix chart
`classifyAndUpdateState`	(Not recommended) Classify data using a trained recurrent neural network and update the network state

Themen

Create Simple Deep Learning Neural Network for Classification
This example shows how to create and train a simple convolutional neural network for deep learning classification.
Train Convolutional Neural Network for Regression
This example shows how to train a convolutional neural network to predict the angles of rotation of handwritten digits.
Time Series Forecasting Using Deep Learning
This example shows how to forecast time series data using a long short-term memory (LSTM) network.
Sequence Classification Using Deep Learning
This example shows how to classify sequence data using a long short-term memory (LSTM) network.
Sequence-to-Sequence Classification Using Deep Learning
This example shows how to classify each time step of sequence data using a long short-term memory (LSTM) network.
Sequence-to-Sequence Regression Using Deep Learning
This example shows how to predict the remaining useful life (RUL) of engines by using deep learning.
Sequence-to-One Regression Using Deep Learning
This example shows how to predict the frequency of a waveform using a long short-term memory (LSTM) neural network.
Create Custom Deep Learning Training Plot
This example shows how to create a custom training plot that updates at each iteration during training of deep learning neural networks using trainnet. (Seit R2023b)
Custom Stopping Criteria for Deep Learning Training
This example shows how to stop training of deep learning neural networks based on custom stopping criteria using trainnet. (Seit R2023b)
Speed Up Deep Neural Network Training
Learn how to accelerate deep neural network training.

Enthaltene Beispiele

Prepare Network for Transfer Learning Using Deep Network Designer

Interactively fine-tune a pretrained deep learning network to learn a new image classification task.

Live Script öffnen

Train Network with Numeric Features

Create and train a simple neural network for deep learning feature data classification.

Live Script öffnen

Train Neural Network with Tabular Data

Train a neural network with tabular data.

Seit R2023b

Live Script öffnen

Build Time Series Forecasting Network Using Deep Network Designer

Create a simple long short-term memory (LSTM) network to forecast time series data using the Deep Network Designer app.

Live Script öffnen

Train Residual Network for Image Classification

Create a deep learning neural network with residual connections and train it on CIFAR-10 data. Residual connections are a popular element in convolutional neural network architectures. Using residual connections improves gradient flow through the network and enables training of deeper networks.

Live Script öffnen

Train Network on Image and Feature Data

Train a network that classifies handwritten digits using both image and feature input data.

Live Script öffnen

Multilabel Image Classification Using Deep Learning

Use transfer learning to train a deep learning model for multilabel image classification.

Live Script öffnen

Build Image-to-Image Regression Network Using Deep Network Designer

Use Deep Network Designer to construct an image-to-image regression network for super resolution.

Live Script öffnen

Adapt Pretrained Audio Network for New Data Using Deep Network Designer

Interactively adapt a pretrained network to classify new audio signals using Deep Network Designer.

Live Script öffnen

Classify Videos Using Deep Learning

Create a network for video classification by combining a pretrained image classification model and an LSTM network.

Live Script öffnen