사용자 지정 훈련 루프

딥러닝 훈련 루프 및 손실 함수 사용자 지정

trainingOptions 함수가 작업에 필요한 훈련 옵션을 제공하지 않거나 사용자 지정한 출력 계층이 필요한 손실 함수를 지원하지 않을 경우에는 사용자 지정 훈련 루프를 정의할 수 있습니다. 계층 그래프가 지원하지 않는 모델의 경우 사용자 지정 모델을 함수로 정의할 수 있습니다. 자세한 내용은 사용자 지정 훈련 루프, 손실 함수 및 신경망 정의 항목을 참조하십시오.

함수

모두 확장

사용자 지정 신경망

`dlnetwork`	Deep learning network for custom training loops
`resetState`	신경망의 상태 파라미터 재설정
`plot`	신경망 아키텍처 플로팅
`addInputLayer`	Add input layer to network
`addLayers`	Add layers to layer graph or network
`removeLayers`	계층 그래프 또는 신경망에서 계층 제거
`connectLayers`	계층 그래프 또는 신경망에서 계층 연결
`disconnectLayers`	계층 그래프 또는 신경망에서 계층 연결 끊기
`replaceLayer`	Replace layer in layer graph or network
`summary`	Print network summary
`initialize`	Initialize learnable and state parameters of a `dlnetwork`
`networkDataLayout`	Deep learning network data layout for learnable parameter initialization
`layerGraph`	딥러닝을 위한 신경망 계층의 그래프
`setL2Factor`	계층의 학습 가능한 파라미터에 대한 L2 정규화 인자 설정
`getL2Factor`	계층의 학습 가능한 파라미터에 대한 L2 정규화 인자 가져오기
`setLearnRateFactor`	계층의 학습 가능한 파라미터에 대한 학습률 인자 설정
`getLearnRateFactor`	계층의 학습 가능한 파라미터에 대한 학습률 인자 가져오기

사용자 지정 훈련 루프

`forward`	Compute deep learning network output for training
`predict`	Compute deep learning network output for inference
`adamupdate`	Update parameters using adaptive moment estimation (Adam)
`rmspropupdate`	Update parameters using root mean squared propagation (RMSProp)
`sgdmupdate`	Update parameters using stochastic gradient descent with momentum (SGDM)
`lbfgsupdate`	Update parameters using limited-memory BFGS (L-BFGS)
`lbfgsState`	State of limited-memory BFGS (L-BFGS) solver
`dlupdate`	Update parameters using custom function
`trainingProgressMonitor`	Monitor and plot training progress for deep learning custom training loops
`updateInfo`	Update information values for custom training loops
`recordMetrics`	Record metric values for custom training loops
`groupSubPlot`	Group metrics in training plot

데이터 처리

`padsequences`	Pad or truncate sequence data to same length
`minibatchqueue`	Create mini-batches for deep learning
`onehotencode`	Encode data labels into one-hot vectors
`onehotdecode`	Decode probability vectors into class labels
`next`	Obtain next mini-batch of data from minibatchqueue
`reset`	Reset minibatchqueue to start of data
`shuffle`	Shuffle data in minibatchqueue
`hasdata`	Determine if minibatchqueue can return mini-batch
`partition`	Partition minibatchqueue

자동 미분

`dlarray`	사용자 지정을 위한 딥러닝 배열
`dlgradient`	Compute gradients for custom training loops using automatic differentiation
`dlfeval`	Evaluate deep learning model for custom training loops
`dims`	`dlarray`의 차원 레이블
`finddim`	Find dimensions with specified label
`stripdims`	Remove `dlarray` data format
`extractdata`	`dlarray`에서 데이터 추출
`isdlarray`	Check if object is `dlarray`

손실 연산

`crossentropy`	Cross-entropy loss for classification tasks
`l1loss`	L₁ loss for regression tasks
`l2loss`	L₂ loss for regression tasks
`huber`	Huber loss for regression tasks
`mse`	Half mean squared error
`ctc`	Connectionist temporal classification (CTC) loss for unaligned sequence classification

함수 가속

`dlaccelerate`	Accelerate deep learning function for custom training loops
`AcceleratedFunction`	Accelerated deep learning function
`clearCache`	Clear accelerated deep learning function trace cache

도움말 항목

사용자 지정 훈련 루프

Train Deep Learning Model in MATLAB
Learn how to training deep learning models in MATLAB^®.
사용자 지정 훈련 루프, 손실 함수 및 신경망 정의
자동 미분을 사용하여 사용자 지정 딥러닝 훈련 루프, 손실 함수 및 신경망을 정의하는 방법을 알아봅니다.
Train Network Using Custom Training Loop
This example shows how to train a network that classifies handwritten digits with a custom learning rate schedule.
Train Sequence Classification Network Using Custom Training Loop
This example shows how to train a network that classifies sequences with a custom learning rate schedule.
Specify Training Options in Custom Training Loop
Learn how to specify common training options in a custom training loop.
Define Model Loss Function for Custom Training Loop
Learn how to define a model loss function for a custom training loop.
Update Batch Normalization Statistics in Custom Training Loop
This example shows how to update the network state in a custom training loop.
Make Predictions Using dlnetwork Object
This example shows how to make predictions using a dlnetwork object by splitting data into mini-batches.
Monitor Custom Training Loop Progress
Track and plot custom training loop progress.
다중 입력 및 다중 출력 신경망
여러 개의 입력값이나 여러 개의 출력값을 갖는 딥러닝 신경망을 정의하고 훈련시키는 방법을 알아봅니다.
Train Network with Multiple Outputs
This example shows how to train a deep learning network with multiple outputs that predict both labels and angles of rotations of handwritten digits.
Classify Videos Using Deep Learning with Custom Training Loop
This example shows how to create a network for video classification by combining a pretrained image classification model and a sequence classification network.
Train Image Classification Network Robust to Adversarial Examples
This example shows how to train a neural network that is robust to adversarial examples using fast gradient sign method (FGSM) adversarial training.
Train Neural ODE Network
This example shows how to train an augmented neural ordinary differential equation (ODE) network.
Train Robust Deep Learning Network with Jacobian Regularization
This example shows how to train a neural network that is robust to adversarial examples using a Jacobian regularization scheme [1].
Solve Ordinary Differential Equation Using Neural Network
This example shows how to solve an ordinary differential equation (ODE) using a neural network.
Assemble Multiple-Output Network for Prediction
This example shows how to assemble a multiple output network for prediction.
Train Network in Parallel with Custom Training Loop
This example shows how to set up a custom training loop to train a network in parallel.
Run Custom Training Loops on a GPU and in Parallel
Speed up custom training loops by running on a GPU, in parallel using multiple GPUs, or on a cluster.

자동 미분

List of Functions with dlarray Support
View the list of functions that support dlarray objects.
Automatic Differentiation Background
Learn how automatic differentiation works.
Use Automatic Differentiation In Deep Learning Toolbox
How to use automatic differentiation in deep learning.

딥러닝 함수 가속

Deep Learning Function Acceleration for Custom Training Loops
Accelerate model functions and model loss functions for custom training loops by caching and reusing traces.
Accelerate Custom Training Loop Functions
This example shows how to accelerate deep learning custom training loop and prediction functions.
Check Accelerated Deep Learning Function Outputs
This example shows how to check that the outputs of accelerated functions match the outputs of the underlying function.
Evaluate Performance of Accelerated Deep Learning Function
This example shows how to evaluate the performance gains of using an accelerated function.

추천 예제

생성적 적대 신경망(GAN) 훈련시키기

이 예제에서는 생성적 적대 신경망을 훈련시켜서 영상을 생성하는 방법을 보여줍니다.

사용자 지정 훈련 루프

함수

사용자 지정 신경망

사용자 지정 훈련 루프

데이터 처리

자동 미분

손실 연산

함수 가속

도움말 항목

사용자 지정 훈련 루프

자동 미분

딥러닝 함수 가속

관련 정보

추천 예제

생성적 적대 신경망(GAN) 훈련시키기

조건부 생성적 적대 신경망(CGAN) 훈련시키기

Train Wasserstein GAN with Gradient Penalty (WGAN-GP)

Train Fast Style Transfer Network

Train a Siamese Network for Dimensionality Reduction

Train a Siamese Network to Compare Images

Image Captioning Using Attention

Sequence-to-Sequence Translation Using Attention

Train Network in Parallel with Custom Training Loop

변분 오토인코더(VAE)를 훈련시켜 영상 생성하기

Train Network Using Cyclical Learning Rate for Snapshot Ensembling

Solve Partial Differential Equations Using Deep Learning

Solve Partial Differential Equation with L-BFGS Method and Deep Learning

Train Neural ODE Network

Dynamical System Modeling Using Neural ODE

Reduced Order Modeling Using Continuous-Time Echo State Network

Node Classification Using Graph Convolutional Network

Multilabel Graph Classification Using Graph Attention Networks

Train Network Using Federated Learning