딥러닝 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 그래프를 사용하여 만들 수 없는 신경망의 경우 사용자 지정 신경망을 함수로 정의할 수 있습니다. 자세한 내용은 사용자 지정 훈련 루프, 손실 함수 및 신경망 정의 항목을 참조하십시오.

함수

모두 확장

사용자 지정 훈련 루프

`dlnetwork`	Deep learning network for custom training loops
`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)
`dlupdate`	Update parameters using custom function
`minibatchqueue`	Create mini-batches for deep learning
`onehotencode`	Encode data labels into one-hot vectors
`onehotdecode`	Decode probability vectors into class labels
`padsequences`	Pad or truncate sequence data to same length
`initialize`	Initialize learnable and state parameters of a `dlnetwork`

자동 미분

`dlarray`	Deep learning array for custom training loops
`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`	Extract data from `dlarray`
`isdlarray`	Check if object is `dlarray`
`functionToLayerGraph`	Convert deep learning model function to a layer graph

딥러닝 연산

`dlconv`	Deep learning convolution
`dltranspconv`	Deep learning transposed convolution
`lstm`	Long short-term memory
`gru`	Gated recurrent unit
`embed`	Embed discrete data
`fullyconnect`	Sum all weighted input data and apply a bias
`dlode45`	Deep learning solution of nonstiff ordinary differential equation (ODE)
`relu`	ReLU(Rectified Linear Unit) 활성화 적용
`leakyrelu`	Apply leaky rectified linear unit activation
`batchnorm`	Normalize data across all observations for each channel independently
`crosschannelnorm`	Cross channel square-normalize using local responses
`groupnorm`	Normalize data across grouped subsets of channels for each observation independently
`instancenorm`	Normalize across each channel for each observation independently
`layernorm`	Normalize data across all channels for each observation independently
`avgpool`	Pool data to average values over spatial dimensions
`maxpool`	Pool data to maximum value
`maxunpool`	Unpool the output of a maximum pooling operation
`softmax`	Apply softmax activation to channel dimension
`sigmoid`	시그모이드 활성화 적용
`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

딥러닝 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.
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.
Train Network on Image and Feature Data
This example shows how to train a network that classifies handwritten digits using both image and feature input data.
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.
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.

모델 함수

Train Network Using Model Function
This example shows how to create and train a deep learning network by using functions rather than a layer graph or a dlnetwork.
Update Batch Normalization Statistics Using Model Function
This example shows how to update the network state in a network defined as a function.
Make Predictions Using Model Function
This example shows how to make predictions using a model function by splitting data into mini-batches.
Initialize Learnable Parameters for Model Function
Learn how to initialize learnable parameters for custom training loops using a model function.

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.

딥러닝 사용자 지정 훈련 루프

함수

사용자 지정 훈련 루프

자동 미분

딥러닝 연산

딥러닝 함수 가속

도움말 항목

사용자 지정 훈련 루프

모델 함수

자동 미분

딥러닝 함수 가속

추천 예제

생성적 적대 신경망(GAN) 훈련시키기

Train Conditional Generative Adversarial Network (CGAN)

Train Wasserstein GAN with Gradient Penalty (WGAN-GP)

Train Fast Style Transfer Network

Train Network Using Custom Training Loop

Train Network Using Model Function

Train a Siamese Network for Dimensionality Reduction

Train a Siamese Network to Compare Images

Image Captioning Using Attention

Multilabel Text Classification Using Deep Learning

Sequence-to-Sequence Translation Using Attention

Sequence-to-Sequence Classification Using 1-D Convolutions

Train Network in Parallel with Custom Training Loop

변분 오토인코더(VAE)를 훈련시켜 영상 생성

Train Network Using Cyclical Learning Rate for Snapshot Ensembling

Solve Partial Differential Equations Using Deep Learning

Solve Partial Differential Equation with LBFGS Method and Deep Learning

Train Neural ODE Network

Dynamical System Modeling Using Neural ODE

Node Classification Using Graph Convolutional Network

Train Network Using Federated Learning