Operazioni
È possibile utilizzare i livelli integrati per la maggior parte delle attività. Se non è presente un livello integrato necessario per l’attività, è possibile definire un proprio livello personalizzato. È possibile definire livelli personalizzati con parametri apprendibili e di stato. Dopo aver definito un livello personalizzato, è possibile verificare che il livello sia valido, compatibile con la GPU e che produca gradienti definiti correttamente. Per saperne di più, vedere Define Custom Deep Learning Layers. Per un elenco dei livelli di supportati, vedere List of Deep Learning Layers.
Utilizzare le operazioni di Deep Learning per sviluppare codice MATLAB® per i livelli personalizzati, i loop di addestramento e le funzioni del modello.
Funzioni
Argomenti
Differenziazione automatica
- Automatic Differentiation Background
Learn how automatic differentiation works. - Use Automatic Differentiation In Deep Learning Toolbox
How to use automatic differentiation in deep learning. - List of Functions with dlarray Support
View the list of functions that supportdlarrayobjects. - Define Custom Deep Learning Operations
Learn how to define custom deep learning operation. (Da R2024a) - Specify Custom Operation Backward Function
This example shows how to define the SReLU operation as a differentiable function and specify a custom backward function. (Da R2024a) - Train Model Using Custom Backward Function
This example shows how to train a deep learning model that contains an operation with a custom backward function. - Create Bidirectional LSTM (BiLSTM) Function
This example shows how to create a bidirectional long-short term memory (BiLSTM) function for custom deep learning functions. (Da R2023b)
Funzioni del modello
- 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 adlnetwork. - 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.
Accelerazione della funzione di Deep Learning
- Deep Learning Function Acceleration
Accelerate model functions and model loss functions 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.
Informazioni complementari
Esempi in primo piano
Train a Twin Network for Dimensionality Reduction
Train a twin neural network with shared weights to compare handwritten digits using dimensionality reduction.
Train a Twin Neural Network to Compare Images
Train a twin neural network with shared weights to identify similar images of handwritten characters.
Image Captioning Using Attention
Train a deep learning model for image captioning using attention.
Sequence-to-Sequence Translation Using Attention
Convert decimal strings to Roman numerals using a recurrent sequence-to-sequence encoder-decoder model with attention.
Solve PDE Using Physics-Informed Neural Network
Train a physics-informed neural network (PINN) to predict the solutions of a partial differential equation (PDE).
Dynamical System Modeling Using Neural ODE
Train a neural network with neural ordinary differential equations (ODEs) to learn the dynamics of a physical system.
Train Neural ODE Network with Control Input
Train a neural ODE that models a swinging pendulum with torque input.
Node Classification Using Graph Convolutional Network
Classify nodes in a graph using a graph convolutional network (GCN).
Multilabel Graph Classification Using Graph Attention Networks
Classify graphs that have multiple independent labels using graph attention networks (GATs).
Train Latent ODE Network with Irregularly Sampled Time-Series Data
Train a latent ordinary differential equation (ODE) autoencoder with time-series data that is sampled at irregular time intervals.
Multivariate Time Series Anomaly Detection Using Graph Neural Network
Detect anomalies in multivariate time series data using a graph neural network (GNN).
