exportONNXNetwork

Export network to ONNX model format

Syntax

exportONNXNetwork(net,filename)

exportONNXNetwork(net,filename,Name,Value)

Description

exportONNXNetwork(net,filename) exports the deep learning network net with weights to the ONNX™ format file filename. If filename exists, then exportONNXNetwork overwrites the file.

This function requires the Deep Learning Toolbox™ Converter for ONNX Model Format support package. If this support package is not installed, then the function provides a download link.

exportONNXNetwork(net,filename,Name,Value) exports a network using additional options specified by one or more name-value pair arguments.

Examples

collapse all

Export Network in ONNX Format

Load a pretrained SqueezeNet convolutional neural network.

net = squeezenet

  DAGNetwork with properties:

         Layers: [68×1 nnet.cnn.layer.Layer]
    Connections: [75×2 table]
     InputNames: {'data'}
    OutputNames: {'ClassificationLayer_predictions'}

Export the network as an ONNX format file in the current folder called squeezenet.onnx. If the Deep Learning Toolbox Converter for ONNX Model Format support package is not installed, then the function provides a link to the required support package in the Add-On Explorer. To install the support package, click the link, and then click Install.

filename = 'squeezenet.onnx';
exportONNXNetwork(net,filename)

Now, you can import the squeezenet.onnx file into any deep learning framework that supports ONNX import.

Input Arguments

collapse all

`net` — Trained network
`SeriesNetwork` object | `DAGNetwork` object

Trained network, specified as a SeriesNetwork or a DAGNetwork object. You can get a trained network by importing a pretrained network (for example, by using the googlenet function) or by training your own network using trainNetwork.

`filename` — Name of file
character vector | string scalar

Name of file, specified as a character vector or string scalar.

Example: 'network.onnx'

Name-Value Pair Arguments

Specify optional comma-separated pairs of Name,Value arguments. Name is the argument name and Value is the corresponding value. Name must appear inside quotes. You can specify several name and value pair arguments in any order as Name1,Value1,...,NameN,ValueN.

Example: exportONNXNetwork(net,filename,'NetworkName','my_net') exports a network and specifies 'my_net' as the network name in the saved ONNX network.

`'NetworkName'` — Name of ONNX network
`'Network'` (default) | character vector | string scalar

Name of ONNX network to store in the saved file, specified as a character vector or a string scalar.

Example: 'my_squeezenet'

`'OpsetVersion'` — Version of ONNX operator set
`8` (default) | `6` | `7` | `9`

Version of ONNX operator set to use in the exported model. If the default operator set does not support the network you are trying to export, then try using a later version. If you import the exported network to another framework and you used an operator set during export that the importer does not support, then the import can fail.

Example: 6

Tips

You can export a trained MATLAB^® deep learning network that includes multiple inputs and multiple outputs to the ONNX model format. To learn about a multiple-input and multiple-output deep learning network, see Multiple-Input and Multiple-Output Networks.
exportONNXNetwork does not export settings or properties related to network training such as training options, learning rate factors, or regularization factors.
If you export a network that contains a layer that the ONNX format does not support, then exportONNXNetwork saves a placeholder ONNX operator in place of the unsupported layer and returns a warning. You cannot import an ONNX network with a placeholder operator into other deep learning frameworks.
Because of architectural differences between MATLAB and ONNX, an exported network can have a different structure compared to the original network. Also, if you import an exported network, layers of a reimported network might differ from the original network.

exportONNXNetwork can export the following:

Networks that have both convolutional and LSTM layers, for example, for video classification applications.
All custom layers (except nnet.onnx.layer.Flatten3dLayer) that are created when importing networks from ONNX or TensorFlow™-Keras using Deep Learning Toolbox Converter for ONNX Model Format or Deep Learning Toolbox Importer for TensorFlow-Keras Models as in the below table.

The following layers:

ONNX Exporter Supported Layers
Deep Learning Toolbox Layers
`additionLayer`
`averagePooling2dLayer`
`averagePooling3dLayer`
`batchNormalizationLayer`
`bilstmLayer`
`ClassificationOutputLayer`
`clippedReluLayer`
`concatenationLayer`
`convolution2dLayer`
`convolution3dLayer`
`crop2dLayer`
`CrossChannelNormalizationLayer`
`depthConcatenationLayer`
`dropoutLayer`
`eluLayer`
`fullyConnectedLayer`
`flattenLayer`
`globalAveragePooling2dLayer`
`globalMaxPooling2dLayer`
`groupedConvolution2dLayer`
`gruLayer`
`imageInputLayer`
`image3dInputLayer`
`leakyReluLayer`
`lstmLayer`
`maxPooling2dLayer`
`maxPooling3dLayer`
`maxUnpooling2dLayer`
`RegressionOutputLayer`
`reluLayer`
`sequenceInputLayer`
`softmaxLayer`
`tanhLayer`
`transposedConv2dLayer`
`transposedConv3dLayer`

ONNX Importer Custom Layers
`nnet.onnx.layer.ClipLayer`
`nnet.onnx.layer.FlattenLayer`
`nnet.onnx.layer.GlobalAveragePooling2dLayer`
`nnet.onnx.layer.IdentityLayer`
`nnet.onnx.layer.PReluLayer`
`nnet.onnx.layer.ElementwiseAffineLayer`
`nnet.onnx.layer.TanhLayer`

Keras Importer Custom Layers
`nnet.keras.layer.FlattenCStyleLayer`
`nnet.keras.layer.GlobalAveragePooling2dLayer`
`nnet.keras.layer.SigmoidLayer`
`nnet.keras.layer.TanhLayer`
`nnet.keras.layer.ZeroPadding2dLayer`

Caffe Importer Custom Layers
`nnet.caffe.layer.TanhLayer`

Computer Vision Toolbox™ Layers
`pixelClassificationLayer`
`rcnnBoxRegressionLayer`
`roiInputLayer`
`roiMaxPooling2dLayer`

Text Analytics Toolbox™ Layers
`wordEmbeddingLayer`

References

[1] Open Neural Network Exchange. https://github.com/onnx/.

[2] ONNX. https://onnx.ai/.

Documentation

exportONNXNetwork

Syntax

Description

Examples

Export Network in ONNX Format

Input Arguments

`net` — Trained network
`SeriesNetwork` object | `DAGNetwork` object

`filename` — Name of file
character vector | string scalar

Name-Value Pair Arguments

`'NetworkName'` — Name of ONNX network
`'Network'` (default) | character vector | string scalar

`'OpsetVersion'` — Version of ONNX operator set
`8` (default) | `6` | `7` | `9`

Tips

References

See Also

Topics

Introduced in R2018a

Deep Learning Toolbox Documentation

Support

Documentation

exportONNXNetwork

Syntax

Description

Examples

Export Network in ONNX Format

Input Arguments

net — Trained network SeriesNetwork object | DAGNetwork object

filename — Name of file character vector | string scalar

Name-Value Pair Arguments

'NetworkName' — Name of ONNX network 'Network' (default) | character vector | string scalar

'OpsetVersion' — Version of ONNX operator set 8 (default) | 6 | 7 | 9

Tips

References

See Also

Topics

Introduced in R2018a

Deep Learning Toolbox Documentation

Support

`net` — Trained network
`SeriesNetwork` object | `DAGNetwork` object

`filename` — Name of file
character vector | string scalar

`'NetworkName'` — Name of ONNX network
`'Network'` (default) | character vector | string scalar

`'OpsetVersion'` — Version of ONNX operator set
`8` (default) | `6` | `7` | `9`