Réseaux préentrainés provenant de plateformes externes

Importer des réseaux préentraînés depuis des plateformes externes de Deep Learning

Importez des réseaux de neurones à partir de TensorFlow™ 2, de TensorFlow-Keras, de PyTorch^®, du format de modèle ONNX™ (Open Neural Network Exchange) et de Caffe. Pour plus d’informations, veuillez consulter Pretrained Deep Neural Networks et Interoperability Between Deep Learning Toolbox, TensorFlow, PyTorch, and ONNX.

Vous devez avoir des support packages pour exécuter les fonctions d’importation dans Deep Learning Toolbox™. Si le support package n’est pas installé, chaque fonction offre un lien de téléchargement vers le support package correspondant dans l’Add-On Explorer. Il est recommandé de télécharger le support package à l’emplacement par défaut de la version de MATLAB^® que vous exécutez. Vous pouvez également télécharger directement les support packages à partir des liens suivants.

La fonction importNetworkFromONNX nécessite Deep Learning Toolbox Converter for ONNX Model Format. Pour télécharger le support package, allez sur https://www.mathworks.com/matlabcentral/fileexchange/67296-deep-learning-toolbox-converter-for-onnx-model-format.
La fonction importNetworkFromPyTorch nécessite Deep Learning Toolbox Converter for PyTorch Models. Pour télécharger le support package, allez sur https://www.mathworks.com/matlabcentral/fileexchange/111925-deep-learning-toolbox-converter-for-pytorch-models.
La fonction importNetworkFromTensorFlow nécessite Deep Learning Toolbox Converter for TensorFlow Models. Pour télécharger le support package, allez sur https://www.mathworks.com/matlabcentral/fileexchange/64649-deep-learning-toolbox-converter-for-tensorflow-models.

Diagram showing the interoperability between Deep Learning Toolbox, TensorFlow, ONNX, and PyTorch.

Fonctions

développer tout

Importation d’un réseau

Importation TensorFlow

importNetworkFromTensorFlow Import TensorFlow network as MATLAB network (depuis R2023b)

Importation PyTorch

importNetworkFromPyTorch Import PyTorch network as MATLAB network (depuis R2022b)

Importation Caffe

`importCaffeNetwork`	Import pretrained convolutional neural network models from Caffe
`importCaffeLayers`	Import convolutional neural network layers from Caffe

Importation ONNX

importNetworkFromONNX Import ONNX network as MATLAB network (depuis R2023b)

Paramètres importés par `importONNXFunction`

`ONNXParameters`	Parameters of imported ONNX network for deep learning (depuis R2020b)
`freezeParameters`	Convert learnable network parameters in `ONNXParameters` to nonlearnable (depuis R2020b)
`unfreezeParameters`	Convert nonlearnable network parameters in `ONNXParameters` to learnable (depuis R2020b)
`addParameter`	Add parameter to `ONNXParameters` object (depuis R2020b)
`removeParameter`	Remove parameter from `ONNXParameters` object (depuis R2020b)

Assemblage d’un réseau

`dlnetwork`	Deep learning neural network (depuis R2019b)
`functionLayer`	Function layer (depuis R2021b)
`replaceLayer`	Replace layer in neural network
`addLayers`	Add layers to neural network
`removeLayers`	Remove layers from neural network

Rubriques

Importation

Interoperability Between Deep Learning Toolbox, TensorFlow, PyTorch, and ONNX
Learn how to import networks from TensorFlow, PyTorch, and ONNX and use the imported networks for common Deep Learning Toolbox workflows. Learn how to export networks to TensorFlow and ONNX.
Tips on Importing Models from TensorFlow, PyTorch, and ONNX
Tips on importing Deep Learning Toolbox networks from TensorFlow, PyTorch, and ONNX.
Import PyTorch® Model Using Deep Network Designer
This example shows how to import a PyTorch® model interactively by using the Deep Network Designer app. (depuis R2023b)
Pretrained Deep Neural Networks
Learn how to download and use pretrained convolutional neural networks for classification, transfer learning and feature extraction.
Inference Comparison Between TensorFlow and Imported Networks for Image Classification
Perform prediction in TensorFlow with a pretrained network, import the network into MATLAB using importTensorFlowNetwork, and then compare inference results between TensorFlow and MATLAB networks.
Inference Comparison Between ONNX and Imported Networks for Image Classification
Perform prediction in ONNX with a pretrained network, import the network into MATLAB using importONNXNetwork, and then compare inference results between ONNX and MATLAB networks.
Classify Images in Simulink with Imported TensorFlow Network
Import a pretrained TensorFlow network using importTensorFlowNetwork, and then use the Predict block for image classification in Simulink^®.
Deploy Imported TensorFlow Model with MATLAB Compiler
Import third-party pretrained networks and deploy the networks using MATLAB Compiler™.
View Autogenerated Custom Layers Using Deep Network Designer
This example shows how to import a pretrained TensorFlow™ network and view the autogenerated layers in Deep Network Designer.
Verify Robustness of ONNX Network
This example shows how to verify the adversarial robustness of an imported ONNX™ deep neural network. (depuis R2024a)

Coexécution avec Python

Classify Images Using TensorFlow Model Predict Block
Classify images using TensorFlow Model Predict block.
Classify Images Using ONNX Model Predict Block
Classify images using ONNX Model Predict block.
Classify Images Using PyTorch Model Predict Block
Classify images using PyTorch Model Predict block.
Predict Responses Using TensorFlow Model Predict Block
Predict Responses Using TensorFlow Model Predict block.
Predict Responses Using ONNX Model Predict Block
Predict Responses Using ONNX Model Predict block.
Predict Responses Using PyTorch Model Predict Block
Predict Responses Using PyTorch Model Predict block.
Predict Responses Using Custom Python Model in Simulink (Statistics and Machine Learning Toolbox)
This example shows how to use the Custom Python Model Predict (Statistics and Machine Learning Toolbox) block for prediction in Simulink®.

Couches personnalisées

Define Custom Deep Learning Layers
Learn how to define custom deep learning layers.