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。
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 Experiment Manager 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。
Deep Network Designer | Design, visualize, and train deep learning networks |
Experiment Manager | Design and run experiments to train and compare deep learning networks |
ConfusionMatrixChart Properties | Confusion matrix chart appearance and behavior |
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.
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。
Train Network Using Custom Training Loop
This example shows how to train a network that classifies handwritten digits with a custom learning rate schedule.
Learn how to improve the accuracy of deep learning networks.
Create a Deep Learning Experiment for Classification
This example shows how to train a deep learning network for classification by using Experiment Manager.
Create a Deep Learning Experiment for Regression
This example shows how to train a deep learning network for regression by using Experiment Manager.
Evaluate Deep Learning Experiments by Using Metric Functions
This example shows how to use metric functions to evaluate the results of an experiment.
Try Multiple Pretrained Networks for Transfer Learning
This example shows how to configure an experiment that replaces layers of different pretrained networks for transfer learning.
Experiment with Weight Initializers for Transfer Learning
This example shows how to configure an experiment that initializes the weights of convolution and fully connected layers using different weight initializers for training.
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®。
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。
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 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.
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.
Deep Dream Images Using GoogLeNet
This example shows how to generate images using deepDreamImage
with the pretrained convolutional neural network GoogLeNet.
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.
此示例说明如何可视化卷积神经网络学习的特征。