本页对应的英文页面已更新，但尚未翻译。 若要查看最新内容，请点击此处访问英文页面。

深度学习调整和可视化

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深度学习训练进度。要提高网络性能，您可以调整训练选项并使用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。

App

Deep Network DesignerDesign, visualize, and train 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 neural network for deep learning
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
occlusionSensitivityDetermine how input data affects output activations by occluding input
confusionchartCreate confusion matrix chart for classification problem
ConfusionMatrixChart PropertiesConfusion matrix chart appearance and behavior
sortClassesSort classes of confusion matrix chart

主题

调整

Set Up Parameters and Train Convolutional Neural Network

Learn how to set up training parameters for a convolutional neural network.

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。

Run Multiple Deep Learning Experiments in Parallel

This example shows how to run multiple deep learning experiments on your local machine.

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.

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.

Investigate Network Predictions Using Class Activation Mapping

This example shows how to use class activation mapping (CAM) to investigate and explain the predictions of a deep convolutional neural network for image classification.

View Network Behavior Using tsne

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

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

使用深度学习对网络摄像头图像进行分类

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。

打开脚本
使用 AlexNet 生成 Deep Dream 图像

使用 AlexNet 生成 Deep Dream 图像

此示例说明如何使用预训练的卷积神经网络 AlexNet 通过 deepDreamImage 生成图像。

打开实时脚本
Grad-CAM Reveals the Why Behind Deep Learning Decisions

Grad-CAM Reveals the Why Behind Deep Learning Decisions

Use the gradient-weighted class activation mapping (Grad-CAM) technique to understand why a deep learning network makes its classification decisions. Grad-CAM, invented by Selvaraju and coauthors [1], uses the gradient of the classification score with respect to the convolutional features determined by the network in order to understand which parts of the image are most important for classification. This example uses the GoogLeNet pretrained network for images.

打开实时脚本
Understand Network Predictions Using Occlusion

Understand Network Predictions Using Occlusion

Use occlusion sensitivity maps to understand why a deep neural network makes a classification decision. Occlusion sensitivity is a simple technique for understanding which parts of an image are most important for a deep network's classification. You can measure a network's sensitivity to occlusion in different regions of the data using small perturbations of the data. Use occlusion sensitivity to gain a high-level understanding of what image features a network uses to make a particular classification, and to provide insight into the reasons why a network can misclassify an image.

打开实时脚本

Deep Learning Toolbox 文档
支持
Introducing Deep Learning with MATLAB

Introducing Deep Learning with MATLAB

Download ebook