실험 관리하기
R2026b여러 초기 조건하에서 신경망 훈련, 훈련 옵션을 대화형 방식으로 조정, 결과 평가
실험 관리자 앱을 사용하면 일련의 하이퍼파라미터 값을 스윕하거나 베이즈 최적화를 사용하여 신경망에 대한 최적의 훈련 옵션을 찾을 수 있습니다. 내장 함수 trainnet을 사용하거나 사용자 지정 훈련 함수를 정의합니다. 훈련 플롯을 사용하여 진행 상황을 모니터링합니다. 혼동행렬과 사용자 지정 메트릭 함수를 사용하여 훈련된 신경망을 평가합니다.
이 페이지에는 AI 워크플로의 실험에 대한 정보가 포함되어 있습니다. 앱 사용에 대한 일반적인 내용은 실험 관리자 항목을 참조하십시오.
앱
| 실험 관리자 | 딥러닝 신경망을 훈련시키고 비교하는 실험을 만들고 실행합니다. |
객체
experiments.Monitor | Update results table and training plots for custom training experiments |
함수
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) (R2024a 이후) |
도움말 항목
실험 구성하기
- 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. - Tune PyTorch Model Using Experiment Manager
Tune hyperparameters of a PyTorch® model by sweeping over combinations of hyperparameter values using Experiment Manager. (R2026b 이후) - Debug Deep Learning Experiments
Diagnose problems in your setup, training, and metric functions. (R2023a 이후) - Keyboard Shortcuts for Experiment Manager
Navigate Experiment Manager using only your keyboard.
trainnet을 사용한 실험
- 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.
사용자 지정 훈련 함수를 사용한 실험
- Use Bayesian Optimization in Custom Training Experiments
Create custom training experiments that use Bayesian optimization. - Run a Custom Training Experiment for Image Comparison
Train a twin neural network to identify similar images of handwritten characters. - Custom Training with Multiple GPUs in Experiment Manager
Configure multiple parallel workers to collaborate on each trial of a custom training experiment.
전이 학습
- 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.
실험 실행 시간 단축하기
- 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®. (R2022a 이후)
추천 예제
Tune Experiment Hyperparameters by Using Bayesian Optimization
Find optimal network hyperparameters and training options for convolutional neural networks.
Choose Training Configurations for LSTM Using Bayesian Optimization
Find optimal data architecture and network configurations for sequence-to-sequence regression using Bayesian optimization.
Use Experiment Manager to Train Generative Adversarial Networks (GANs)
Create a custom training experiment to generate images of flowers.
