Gestionar experimentos

Entrene redes en distintas condiciones iniciales, ajuste las opciones de entrenamiento de forma interactiva y evalúe sus resultados

Use la app Experiment Manager para buscar las mejores opciones de entrenamiento para redes neuronales realizando un barrido a través de un intervalo de valores de hiperparámetros o usando la optimización bayesiana. Use la función integrada trainnet o defina su propia función de entrenamiento personalizada. Monitorice su progreso mediante gráficas de entrenamiento. Utilice matrices de confusión y funciones métricas personalizadas para evaluar la red entrenada.

Esta página contiene información sobre experimentos para sus flujos de trabajo de IA. Para obtener más información sobre cómo usar esta app, consulte Experiment Manager.

Apps

Experiment Manager

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

Objetos

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

Funciones

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

Temas

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

Solución de problemas

Debug Deep Learning Experiments

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

Información relacionada

Ejemplos destacados

Try Multiple Pretrained Networks for Transfer Learning

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

Desde R2020a

Abrir script

Experiment with Weight Initializers for Transfer Learning

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

Desde R2020a

Abrir script

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.

Abrir script