Main Content

本页的翻译已过时。点击此处可查看最新英文版本。

深度学习调整和可视化

管理试验,绘制训练进度、评估准确度、进行预测、调整训练选项以及将网络学习的特征可视化

使用内置的网络准确度和损失图监控训练进度。要提高网络性能,您可以调整训练选项并使用试验管理器或贝叶斯优化来搜索最优超参数。要研究经过训练的网络,您可以将网络学习的特征可视化并创建 Deep Dream 可视化。通过使用新数据进行预测来测试经过训练的网络。管理在各种初始条件下训练网络的深度学习试验,并比较结果。

App

深度网络设计器Design, visualize, and train deep learning networks
试验管理器Design and run experiments to train and compare deep learning networks

函数

全部展开

analyzeNetworkAnalyze deep learning network architecture
plotPlot neural network layer graph
trainingOptionsOptions for training deep learning neural network
trainNetworkTrain deep learning neural network
activationsCompute deep learning network layer activations
predictPredict responses using a trained deep learning neural network
classifyClassify data using a trained deep learning neural network
predictAndUpdateStatePredict responses using a trained recurrent neural network and update the network state
classifyAndUpdateStateClassify data using a trained recurrent neural network and update the network state
resetStateReset the state of a recurrent neural network
deepDreamImageVisualize network features using deep dream
occlusionSensitivityExplain network predictions by occluding the inputs
imageLIMEExplain network predictions using LIME
confusionchartCreate confusion matrix chart for classification problem
sortClassesSort classes of confusion matrix chart

属性

ConfusionMatrixChart PropertiesConfusion matrix chart appearance and behavior

主题

调整

设置参数并训练卷积神经网络

了解如何为卷积神经网络设置训练参数。

Resume Training from Checkpoint Network

This example shows how to save checkpoint networks while training a deep learning network and resume training from a previously saved network.

使用贝叶斯优化进行深度学习

此示例说明如何将贝叶斯优化应用于深度学习并找到卷积神经网络的最优网络超参数和训练选项。

并行训练深度学习网络

此示例说明如何在本地计算机上运行多个深度学习试验。使用此示例作为模板,您可以修改网络层和训练选项,以满足您的具体应用需要。无论您有一个还是多个 GPU,都可以使用这种方法。如果您只有一个 GPU,网络会在后台逐个进行训练。本示例中的方法使您能够在进行深度学习试验时继续使用 MATLAB®。

Train Network Using Custom Training Loop

This example shows how to train a network that classifies handwritten digits with a custom learning rate schedule.

Deep Learning Tips and Tricks

Learn how to improve the accuracy of deep learning networks.

试验

Create a Deep Learning Experiment for Classification

Train a deep learning network for classification using Experiment Manager.

Create a Deep Learning Experiment for Regression

Train a deep learning network for regression using Experiment Manager.

Use Experiment Manager to Train Networks in Parallel

Train deep networks in parallel using Experiment Manager.

Evaluate Deep Learning Experiments by Using Metric Functions

Use metric functions to evaluate the results of an experiment.

Tune Experiment Hyperparameters by Using Bayesian Optimization

Find optimal network hyperparameters and training options for convolutional neural networks.

Try Multiple Pretrained Networks for Transfer Learning

Configure an experiment that replaces layers of different pretrained networks for transfer learning.

Experiment with Weight Initializers for Transfer Learning

Configure an experiment that initializes the weights of convolution and fully connected layers using different weight initializers.

可视化

使用深度学习对网络摄像头图像进行分类

此示例说明如何使用预训练的深度卷积神经网络 GoogLeNet 实时对来自网络摄像头的图像进行分类。

监控深度学习训练进度

在训练深度学习网络时,监控训练进度通常很有用。通过在训练过程中绘制各种指标,您可以了解训练的进度情况。例如,您可以确定网络准确度是否改善以及改善速度,还可以确定网络是否开始过拟合训练数据。

Grad-CAM Reveals the Why Behind Deep Learning Decisions

This example shows how to use the gradient-weighted class activation mapping (Grad-CAM) technique to understand why a deep learning network makes its classification decisions.

Understand Network Predictions Using Occlusion

This example shows how to use occlusion sensitivity maps to understand why a deep neural network makes a classification decision.

Understand Network Predictions Using LIME

This example shows how to use locally interpretable model-agnostic explanations (LIME) to understand why a deep neural network makes a classification decision.

Investigate Classification Decisions Using Gradient Attribution Techniques

This example shows how to use gradient attribution maps to investigate which parts of an image are most important for classification decisions made by a deep neural network.

使用类激活映射调查网络预测

此示例说明如何使用类激活映射 (CAM) 来调查和解释用于图像分类的深度卷积神经网络的预测。

Visualize Image Classifications Using Maximal and Minimal Activating Images

This example shows how to use a data set to find out what activates the channels of a deep neural network.

View Network Behavior Using tsne

This example shows how to use the tsne function to view activations in a trained network.

Monitor GAN Training Progress and Identify Common Failure Modes

Learn how to diagnose and fix some of the most common failure modes in GAN training.

使用 GoogLeNet 的 Deep Dream 图像

此示例说明如何使用 deepDreamImage 和预训练卷积神经网络 GoogLeNet 生成图像。

可视化卷积神经网络的激活区域

此示例说明如何将图像馈送到卷积神经网络并显示网络的不同层的激活区域。通过将激活区域与原始图像进行比较,检查激活区域并发现网络学习的特征。发现较浅层中的通道学习颜色和边缘等简单特征,而较深层中的通道学习眼睛等复杂特征。以这种方式识别特征可以帮助您了解网络学习的内容。

Visualize Activations of LSTM Network

This example shows how to investigate and visualize the features learned by LSTM networks by extracting the activations.

可视化卷积神经网络的特征

此示例说明如何可视化卷积神经网络学习的特征。

特色示例