Gestione degli esperimenti
Utilizzare l'applicazione Experiment Manager per trovare le opzioni di addestramento ottimali per le reti neurali, spaziando in un intervallo di valori di iperparametri o utilizzando l'ottimizzazione bayesiana. Utilizzare la funzione integrata trainnet o definire una funzione di addestramento personalizzata. Monitorare i progressi utilizzando i grafici di addestramento. Utilizzare le matrici di confusione e le funzioni metriche personalizzate per valutare la rete addestrata.
Questa pagina contiene informazioni sugli esperimenti per i workflow di IA. Per informazioni generali sull'utilizzo dell'applicazione, vedere Experiment Manager.
App
| Experiment Manager | Create and run experiments to train and compare deep learning networks |
Oggetti
experiments.Monitor | Update results table and training plots for custom training experiments |
Funzioni
groupSubPlot | Group metrics in experiment training plot |
recordMetrics | Record metric values in experiment results table and training plot |
updateInfo | Update information columns in experiment results table |
yscale | Set training plot y-axis scale (linear or logarithmic) (Da R2024a) |
Argomenti
- Choose Strategy for Exploring Experiment Parameters
Choose between the exhaustive sweep, random sampling, and Bayesian optimization strategies for exploring your experiment parameters using Experiment Manager.
- Run Experiments in Parallel
Run multiple simultaneous trials or one trial at a time on multiple workers.
- Offload Experiments as Batch Jobs to a Cluster
Run experiments on a cluster so you can continue working or close MATLAB®. (Da R2022a)
- Keyboard Shortcuts for Experiment Manager
Navigate Experiment Manager using only your keyboard.
- Compare Classification Network Architectures Using Experiment
Train a deep learning network for classification using Experiment Manager.
- Compare Dropout Probabilities and Filter Configurations for Image Regression Using Experiment
Train a deep learning network for regression using Experiment Manager.
- 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.
- Use Bayesian Optimization in Custom Training Experiments
Create custom training experiments that use Bayesian optimization. (Da R2021b)
Risoluzione dei problemi
Debug Deep Learning Experiments
Diagnose problems in your setup, training, and metric functions. (Da R2023a)
Informazioni complementari
Esempi in primo piano
Try Multiple Pretrained Networks for Transfer Learning
Configure an experiment that replaces layers of different pretrained networks for transfer learning.
Experiment with Weight Initializers for Transfer Learning
Configure an experiment that initializes the weights of convolution and fully connected layers using different weight initializers.
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.
Choose Training Configurations for LSTM Using Bayesian Optimization
Find optimal data architecture and network configurations for sequence-to-sequence regression using Bayesian optimization.
Run a Custom Training Experiment for Image Comparison
Train a twin neural network to identify similar images of handwritten characters.
Use Experiment Manager to Train Generative Adversarial Networks (GANs)
Create a custom training experiment to generate images of flowers.
Custom Training with Multiple GPUs in Experiment Manager
Configure multiple parallel workers to collaborate on each trial of a custom training experiment.
