管理试验

在多个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

使用试验管理器，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 trainnet 或定义您自己的自定义训练函数。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。

此页包含有关 AI 工作流试验的信息。有关使用该 App 的一般信息，请参阅试验管理器。

App

试验管理器

Design and run experiments to train and compare deep learning networks (自 R2020a 起)

对象

experiments.Monitor Update results table and training plots for custom training experiments (自 R2021a 起)

函数

`groupSubPlot`	Group metrics in experiment training plot (自 R2021a 起)
`recordMetrics`	Record metric values in experiment results table and training plot (自 R2021a 起)
`updateInfo`	Update information columns in experiment results table (自 R2021a 起)
`yscale`	Set training plot y-axis scale (linear or logarithmic) (自 R2024a 起)

主题

Run Experiments in Parallel
Run multiple simultaneous trials or one trial at a time on multiple workers. (自 R2020b 起)
Offload Experiments as Batch Jobs to a Cluster
Run experiments on a cluster so you can continue working or close MATLAB^®. (自 R2022a 起)
Keyboard Shortcuts for Experiment Manager
Navigate Experiment Manager using only your keyboard.
Create a Deep Learning Experiment for Classification
Train a deep learning network for classification using Experiment Manager. (自 R2020a 起)
Create a Deep Learning Experiment for Regression
Train a deep learning network for regression using Experiment Manager. (自 R2020a 起)
Evaluate Deep Learning Experiments by Using Metric Functions
Use metric functions to evaluate the results of an experiment. (自 R2020a 起)
Tune Experiment Hyperparameters by Using Bayesian Optimization
Find optimal network hyperparameters and training options for convolutional neural networks. (自 R2020b 起)
Use Bayesian Optimization in Custom Training Experiments
Create custom training experiments that use Bayesian optimization. (自 R2021b 起)

疑难解答

Debug Deep Learning Experiments

Diagnose problems in your setup, training, and metric functions. (自 R2023a 起)

精选示例

Try Multiple Pretrained Networks for Transfer Learning

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

自 R2020a 起

打开脚本

Experiment with Weight Initializers for Transfer Learning

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

自 R2020a 起

打开脚本

Audio Transfer Learning Using Experiment Manager

Configure an experiment that compares the performance of multiple pretrained networks applied to a speech command recognition task using transfer learning.

打开脚本