La traducción de esta página aún no se ha actualizado a la versión más reciente. Haga clic aquí para ver la última versión en inglés.

Redes preentrenadas desde plataformas externas

Importe redes preentrenadas desde plataformas externas de deep learning

Importe redes y gráficas de capas de TensorFlow™ 2, TensorFlow-Keras, PyTorch^®, el formato de modelos ONNX™ (Open Neural Network Exchange) y Caffe. Para obtener más información, consulte Redes neuronales profundas preentrenadas y Interoperability Between Deep Learning Toolbox, TensorFlow, PyTorch, and ONNX.

Debe disponer de paquetes de soporte para ejecutar las funciones de importación en Deep Learning Toolbox™. Si el paquete de soporte no está instalado, cada función proporciona un enlace de descarga al paquete de soporte correspondiente en Add-On Explorer. La práctica recomendada es descargar el paquete de soporte en la ubicación predeterminada para la versión de MATLAB^® que está ejecutando. También puede descargar directamente los paquetes de soporte desde los siguientes enlaces.

La funciones importONNXNetwork, importONNXLayers, importONNXFunction requieren Deep Learning Toolbox Converter for ONNX Model Format. Para descargar el paquete de soporte, vaya a https://www.mathworks.com/matlabcentral/fileexchange/67296-deep-learning-toolbox-converter-for-onnx-model-format.
Las funciones importTensorFlowNetwork, importTensorFlowLayers, importKerasNetwork y importKerasLayers requieren Deep Learning Toolbox Converter for TensorFlow Models. Para descargar el paquete de soporte, vaya a https://www.mathworks.com/matlabcentral/fileexchange/64649-deep-learning-toolbox-converter-for-tensorflow-models.
La función importNetworkFromPyTorch requiere Deep Learning Toolbox Converter for PyTorch Models. Para descargar el paquete de soporte, vaya a https://www.mathworks.com/matlabcentral/fileexchange/111925.

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

Funciones

expandir todo

Importación de redes

Importación de TensorFlow

`importTensorFlowNetwork`	(To be removed) Import pretrained TensorFlow network (desde R2021a)
`importTensorFlowLayers`	(To be removed) Import layers from TensorFlow network (desde R2021a)
`importKerasNetwork`	(To be removed) Import pretrained Keras network and weights
`importKerasLayers`	(To be removed) Import layers from Keras network

Importación de PyTorch

importNetworkFromPyTorch Import PyTorch network as MATLAB network (desde R2022b)

Importación de Caffe

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

Importación de ONNX

`importONNXNetwork`	(To be removed) Import pretrained ONNX network
`importONNXLayers`	(To be removed) Import layers from ONNX network
`importONNXFunction`	Import pretrained ONNX network as a function (desde R2020b)

Parámetros importados mediante `importONNXFunction`

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

Montaje de redes

`functionLayer`	Function layer (desde R2021b)
`findPlaceholderLayers`	Find placeholder layers in network architecture imported from Keras or ONNX
`replaceLayer`	Replace layer in layer graph or network
`assembleNetwork`	Assemble deep learning network from pretrained layers
`PlaceholderLayer`	Layer replacing an unsupported Keras or ONNX layer
`addLayers`	Add layers to layer graph or network
`removeLayers`	Remove layers from layer graph or network

Temas

Importación

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.
Redes neuronales profundas preentrenadas
Aprenda a descargar y utilizar redes neuronales convolucionales preentrenadas para clasificación, transferencia del aprendizaje y extracción de características.
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.
Assemble Network from Pretrained Keras Layers
This example shows how to import the layers from a pretrained Keras network, replace the unsupported layers with custom layers, and assemble the layers into a network ready for prediction.
Replace Unsupported Keras Layer with Function Layer
This example shows how to import the layers from a pretrained Keras network, replace the unsupported layers with function layers, and assemble the layers into a network ready for prediction.
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™.
Select Function to Import ONNX Pretrained Network
Import an ONNX pretrained network using importONNXNetwork, importONNXLayers, or importONNXFunction.
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.

Capas personalizadas

Define Custom Deep Learning Layers
Learn how to define custom deep learning layers.
Define Custom Deep Learning Intermediate Layers
Learn how to define custom deep learning intermediate layers.
Define Custom Deep Learning Output Layers
Learn how to define custom deep learning output layers.