La traduction de cette page n'est pas à jour. Cliquez ici pour voir la dernière version en anglais.
Fondamentaux de la génération de code pour le Deep Learning
R2025bVous pouvez utiliser MATLAB® Coder™ avec Deep Learning Toolbox™ pour générer du code C++ à partir d’un CNN (réseau de neurones à convolution) entraîné. Vous pouvez ensuite déployer le code généré sur une plateforme embarquée utilisant un processeur Intel® ou ARM®. Il est également possible de générer du code C ou C++ à partir d’un CNN entraîné ne dépendant pas de bibliothèques tierces.
Fonctions
codegen | Generate C or C++ code from MATLAB code |
coder.loadDeepLearningNetwork | Load deep learning network model |
coder.DeepLearningConfig | Create deep learning code generation configuration objects |
coder.DeepLearningCodeConfig | Parameters to configure deep learning code generation that does not depend on third-party libraries |
coder.ai.enableParameterUpdate | Enables run-time update of network parameters (depuis R2025a) |
coder.ARMNEONConfig | (To be removed) Parameters to configure deep learning code generation with the ARM Compute Library |
coder.CMSISNNConfig | (To be removed) Parameters to configure deep learning code generation with the CMSIS-NN library for Cortex-M targets (depuis R2022a) |
coder.MklDNNConfig | Parameters to configure deep learning code generation with the Intel Math Kernel Library for Deep Neural Networks |
analyzeNetworkForCodegen | Analyze deep learning network for code generation (depuis R2022b) |
coder.regenerateDeepLearningParameters | Regenerate files containing network learnables and states parameters |
Paramètres de configuration du code
| Deep learning target library | Target library for deep learning code generation |
| Learnables compression | Compression type |
| ARM Compute Library version | (To be removed) Version of ARM Compute Library |
| ARM Compute architecture | (To be removed) ARM architecture supported in the target hardware |
| Data type (ARM Compute) | (To be removed) Inference computation precision |
| Calibration result file path (ARM Compute) | (To be removed) Location of calibration MAT file |
| Data type (CMSIS-NN) | (To be removed) Inference computation precision |
| Calibration result file path (CMSIS-NN) | (To be removed) Location of calibration MAT file |
Rubriques
- Prerequisites for Deep Learning with MATLAB Coder
Install products and configure environment for code generation for deep learning networks.
- Workflow for Deep Learning Code Generation with MATLAB Coder
Generate code for prediction from a pretrained network.
- Load Pretrained Networks for Code Generation
Create a
dlnetworkobject, or an object detector for code generation. - Analyze Network for Code Generation
Check code generation compatibility of a deep learning network.
- Networks and Layers Supported for Code Generation
Choose a convolutional neural network that is supported for your target processor.
- Code Generation for dlarray
Use deep learning arrays in MATLAB code intended for code generation.
- Generate Generic C/C++ Code for Deep Learning Networks
Generate C/C++/CUDA code for prediction from a deep learning network that does not depend on third-party libraries.
- Update Network Parameters at Run Time
Update deep learning network parameters at run-time without regenerating code.
- Compress Networks Learnables in bfloat16 Format
Perform learnables compression and generate C/C++ code in Brain Floating Point format, bfloat16.
- Optimize C/C++ Code Performance for Deep Learning Applications without Deep Learning Libraries
Code generation configuration settings that optimize the performance of the generated C/C++ code for a deep learning network.
- Code Generation for Deep Learning Networks with MKL-DNN
Generate C++ code for prediction from a deep learning network, targeting an Intel CPU.
- Code Generation for Deep Learning Networks with ARM Compute Library
Generate C++ code for prediction from a deep learning network, targeting an ARM processor.
- Cross-Compile Deep Learning Code That Uses ARM Compute Library
Generate library or executable code on host computer for deployment on ARM hardware target.
- Generate int8 Code for Deep Learning Networks
Quantize and generate code for a pretrained convolutional neural network.
- Update Network Parameters After Code Generation
Perform post code generation updates of deep learning network parameters.
Informations connexes
- Introduction à Deep Learning Toolbox (Deep Learning Toolbox)
- Deep Learning with GPU Coder (GPU Coder)
Sélection d՚exemples
Generate Digit Images Using Variational Autoencoder on Intel CPUs
Generate code for a trained VAE dlnetwork to generate hand-drawn digits.
Cross Compile Deep Learning Code for ARM Neon Targets
Generate library or executable code on host computer for deployment on ARM hardware target.
Post-Code-Generation Update of Deep Learning Network Parameters
Incrementally update the network learnables of a deep learning network application running on edge devices such as Raspberry Pi®. This example uses a cart-pole reinforcement learning application to illustrate:
