사용자 지정 훈련 루프

시퀀스 및 테이블 형식 데이터를 위한 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
`trainingProgressMonitor`	Monitor and plot training progress for deep learning custom training loops
`minibatchqueue`	Create mini-batches for deep learning
`padsequences`	Pad or truncate sequence data to same length
`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

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

딥러닝 연산

`dlconv`	Deep learning convolution
`dltranspconv`	Deep learning transposed convolution
`lstm`	장단기 기억
`gru`	Gated recurrent unit
`attention`	Dot-product attention
`embed`	Embed discrete data
`fullyconnect`	Sum all weighted input data and apply a bias
`dlode45`	Deep learning solution of nonstiff ordinary differential equation (ODE)
`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

활성화

`relu`	ReLU(Rectified Linear Unit) 활성화 적용
`leakyrelu`	Apply leaky rectified linear unit activation
`gelu`	Apply Gaussian error linear unit (GELU) activation
`softmax`	Apply softmax activation to channel dimension
`sigmoid`	시그모이드 활성화 적용

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 Sequence Classification Network Using Custom Training Loop
This example shows how to train a network that classifies sequences with a custom learning rate schedule.
Monitor Custom Training Loop Progress
Track and plot custom training loop progress.
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 Neural ODE Network
This example shows how to train an augmented neural ordinary differential equation (ODE) network.
Solve Ordinary Differential Equation Using Neural Network
This example shows how to solve an ordinary differential equation (ODE) using a neural network.