Main Content

本页的翻译已过时。点击此处可查看最新英文版本。

深度学习试验

在各种初始条件下训练网络,以交互方式调整训练选项,并评估结果

通过扫描一系列超参数值或使用贝叶斯优化,找到神经网络的最佳训练选项。使用内置函数 trainNetwork 或定义您自己的自定义训练函数。通过并行运行试验,同时测试不同训练配置。使用训练图监控进度。使用混淆矩阵和自定义度量函数来评估经过训练的网络。通过分类和筛选完善试验。使用注释来记录观测值。

App

试验管理器Design and run experiments to train and compare deep learning networks

对象

experiments.MonitorUpdate results table and training plots for custom training experiments

函数

groupSubPlotGroup metrics in experiment training plot
recordMetricsRecord metric values in experiment results table and training plot
updateInfoUpdate information columns in experiment results table

主题

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

Run multiple trials of an experiment at the same time.

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.

Adapt Code Generated in Deep Network Designer for Use in Experiment Manager

Use Experiment Manager to tune the hyperparameters of a network trained in Deep Network Designer.

特色示例