Pretrained Networks from External Platforms

Import pretrained networks from external deep learning platforms

Import networks and layer graphs from TensorFlow™ 2, TensorFlow-Keras, PyTorch^®, the ONNX™ (Open Neural Network Exchange) model format, and Caffe. For more information, see Pretrained Deep Neural Networks and Interoperability Between Deep Learning Toolbox, TensorFlow, PyTorch, and ONNX.

You must have support packages to run the import functions in Deep Learning Toolbox™. If the support package is not installed, each function provides a download link to the corresponding support package in the Add-On Explorer. A recommended practice is to download the support package to the default location for the version of MATLAB^® you are running. You can also directly download the support packages from the following links.

The importONNXNetwork, importONNXLayers, importONNXFunction, functions require Deep Learning Toolbox Converter for ONNX Model Format. To download the support package, go to https://www.mathworks.com/matlabcentral/fileexchange/67296-deep-learning-toolbox-converter-for-onnx-model-format.
The importTensorFlowNetwork, importTensorFlowLayers, importKerasNetwork, and importKerasLayers functions require Deep Learning Toolbox Converter for TensorFlow Models. To download the support package, go to https://www.mathworks.com/matlabcentral/fileexchange/64649-deep-learning-toolbox-converter-for-tensorflow-models.
The importNetworkFromPyTorch function requires Deep Learning Toolbox Converter for PyTorch Models. To download the support package, go to https://www.mathworks.com/matlabcentral/fileexchange/111925.

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

Functions

expand all

Network Import

TensorFlow Import

`importTensorFlowNetwork`	Import pretrained TensorFlow network
`importTensorFlowLayers`	Import layers from TensorFlow network
`importKerasNetwork`	Import pretrained Keras network and weights
`importKerasLayers`	Import layers from Keras network

PyTorch Import

importNetworkFromPyTorch Import PyTorch model as MATLAB network

Caffe Import

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

ONNX Import

`importONNXNetwork`	Import pretrained ONNX network
`importONNXLayers`	Import layers from ONNX network
`importONNXFunction`	Import pretrained ONNX network as a function

Parameters Imported by `importONNXFunction`

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

Network Assembly

`functionLayer`	Function layer
`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

Topics

Import

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 or layer graphs from TensorFlow, PyTorch, and ONNX.
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.
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.

Custom Layers

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.