可视化深度神经网络 -凯发k8网页登录

绘制训练进度、评估准确度、解释预测以及将图像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。使用可视化方法，如 grad-cam、遮挡敏感度、lime 和 deep dream，研究经过训练的网络。

app

设计、可视化和训练深度学习网络

函数

绘图

`analyzenetwork`	analyze deep learning network architecture
`trainingprogressmonitor`	monitor and plot training progress for deep learning custom training loops
	update information values for custom training loops
	record metric values for custom training loops
	group metrics in training plot
	plot neural network architecture

特征可视化

	计算深度学习网络层激活
	visualize network features using deep dream
	explain network predictions by occluding the inputs
	explain network predictions using lime
	explain network predictions using grad-cam
	create confusion matrix chart for classification problem
	sort classes of confusion matrix chart
	receiver operating characteristic (roc) curve and performance metrics for binary and multiclass classifiers
	compute additional classification performance metrics
	compute performance metrics for average receiver operating characteristic (roc) curve in multiclass problem

属性

	confusion matrix chart appearance and behavior
	receiver operating characteristic (roc) curve appearance and behavior

主题

可解释性

deep learning visualization methods
learn about and compare deep learning visualization methods.
this example shows how to use occlusion sensitivity maps to understand why a deep neural network makes a classification decision.
this example shows how to use locally interpretable model-agnostic explanations (lime) to investigate the robustness of a deep convolutional neural network trained to classify spectrograms.
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。
this example shows how to use a data set to find out what activates the channels of a deep neural network.
this example shows how to use the tsne function to view activations in a trained network.
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。通过将激活区域与原始图像进行比较，检查激活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。
此示例说明如何可视化卷积神经网络学习的特征。

训练进度和性能

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。
此示例说明如何监控深度学习网络的训练过程。
track and plot custom training loop progress.
learn how to diagnose and fix some of the most common failure modes in gan training.
use rocmetrics to examine the performance of a classification algorithm on a test data set.
this example shows how to use receiver operating characteristic (roc) curves to compare the performance of deep learning models.

精选示例

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.

understand network predictions using lime

use locally interpretable model-agnostic explanations (lime) to understand why a deep neural network makes a classification decision.