importONNXNetwork

Import pretrained ONNX network

Syntax

net = importONNXNetwork(modelfile,'OutputLayerType',outputtype)

net = importONNXNetwork(modelfile,'OutputLayerType',outputtype,'Classes',classes)

Description

net = importONNXNetwork(modelfile,'OutputLayerType',outputtype) imports a pretrained network from the ONNX™ (Open Neural Network Exchange) file modelfile and specifies the output layer type of the imported network.

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.

net = importONNXNetwork(modelfile,'OutputLayerType',outputtype,'Classes',classes) additionally specifies the classes for a classification network.

Examples

Download and Install Deep Learning Toolbox Converter for ONNX Model Format

Download and install the Deep Learning Toolbox Converter for ONNX Model Format support package.

Type importONNXNetwork at the command line.

importONNXNetwork

If Deep Learning Toolbox Converter for ONNX Model Format 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. Check that the installation is successful by importing the network from the model file 'cifarResNet.onnx' at the command line. If the support package is installed, then the function returns a DAGNetwork object.

modelfile = 'cifarResNet.onnx';
classes = ["airplane" "automobile" "bird" "cat" "dee" "dog" "frog" "horse" "ship" "truck"];
net = importONNXNetwork(modelfile,'OutputLayerType','classification','Classes',classes)

net = 

  DAGNetwork with properties:

         Layers: [77×1 nnet.cnn.layer.Layer]
    Connections: [85×2 table]

Import ONNX Network

Import a residual neural network trained on the CIFAR-10 data set. Specify the file containing the ONNX network, its output type, and its output classes.

modelfile = 'cifarResNet.onnx';
classes = ["airplane" "automobile" "bird" "cat" "deer" "dog" "frog" "horse" "ship" "truck"];
net = importONNXNetwork(modelfile,'OutputLayerType','classification','Classes',classes)

net = 
  DAGNetwork with properties:

         Layers: [77×1 nnet.cnn.layer.Layer]
    Connections: [85×2 table]
     InputNames: {'Input_input'}
    OutputNames: {'ClassificationLayer_softmax'}

Analyze the imported network.

analyzeNetwork(net)

Input Arguments

modelfile — Name of ONNX model file

character vector | string scalar

Name of ONNX model file containing the network, specified as a character vector or a string scalar. The file must be in the current folder, in a folder on the MATLAB^® path, or you must include a full or relative path to the file.

Example: 'cifarResNet.onnx'

outputtype — Type of output layer

'classification' | 'regression' | 'pixelclassification'

Type of the output layer that the function appends to the end of the imported network, specified as 'classification', 'regression', or 'pixelclassification'. Using 'pixelclassification' appends a pixelClassificationLayer (Computer Vision Toolbox) object (requires Computer Vision Toolbox™).

If a network in modelfile has multiple outputs, then you cannot specify the output layer types using this argument. Use importONNXLayers instead. importONNXLayers inserts placeholder layers for the outputs. After importing, you can find and replace the placeholder layers by using findPlaceholderLayers and replaceLayer, respectively.

Example: 'regression'

classes — Classes of the output layer

'auto' (default) | categorical vector | string array | cell array of character vectors

Classes of the output layer, specified as a categorical vector, string array, cell array of character vectors, or 'auto'. If Classes is 'auto', then the software sets the classes to categorical(1:N), where N is the number of classes. If you specify a string array or cell array of character vectors str, then the software sets the classes of the output layer to categorical(str,str).

Data Types: char | categorical | string | cell

Output Arguments

net — Pretrained network

DAGNetwork object

Pretrained network, returned as DAGNetwork object.

Limitations

• importONNXNetwork supports ONNX versions as follows:

  • The function supports ONNX intermediate representation version 6.

  • The function fully supports ONNX operator sets 6, 7, 8, and 9.

  • The function offers limited support for ONNX operator sets 10 and 11.

Note

If you import an exported network, layers of the reimported network might differ from the original network and might not be supported.

More About

Supported ONNX Layers

importONNXNetwork supports the following ONNX layers, with some limitations:

ONNX Layer	Deep Learning Toolbox Layer
Add	additionLayer or nnet.onnx.layer.ElementwiseAffineLayer
AveragePool	averagePooling2dLayer
BatchNormalization	batchNormalizationLayer
Concat	concatenationLayer
Constant	None (Imported as weights)
Conv*	convolution2dLayer
ConvTranspose	transposedConv2dLayer
Dropout	dropoutLayer
Elu	eluLayer
Gemm	fullyConnectedLayer if ONNX network is recurrent, otherwise nnet.onnx.layer.FlattenLayer followed by convolution2dLayer
GlobalAveragePool	globalAveragePooling2dLayer
GlobalMaxPool	globalMaxPooling2dLayer
GRU	gruLayer
InstanceNormalization	groupNormalizationLayer with numGroups specified as "channel-wise"
LeakyRelu	leakyReluLayer
LRN	CrossChannelNormalizationLayer
LSTM	lstmLayer or bilstmLayer
MatMul	fullyConnectedLayer if ONNX network is recurrent, otherwise convolution2dLayer
MaxPool	maxPooling2dLayer
Mul	multiplicationLayer
Relu	reluLayer or clippedReluLayer
Sigmoid	sigmoidLayer
Softmax	softmaxLayer
Sum	additionLayer
Tanh	tanhLayer

*If the pads attribute of the Conv operator is a vector with only two elements [p1,p2], importONNXNetwork imports Conv as a convolution2dLayer with the name-value argument 'Padding' specified as [p1,p2,p1,p2].

ONNX Layer	ONNX Importer Custom Layer
Clip	nnet.onnx.layer.ClipLayer
Div	nnet.onnx.layer.ElementwiseAffineLayer
Flatten	nnet.onnx.layer.FlattenLayer or nnet.onnx.layer.Flatten3dLayer
Identity	nnet.onnx.layer.IdentityLayer
ImageScaler	nnet.onnx.layer.ElementwiseAffineLayer
PRelu	nnet.onnx.layer.PReluLayer
Reshape	nnet.onnx.layer.FlattenLayer
Sub	nnet.onnx.layer.ElementwiseAffineLayer

ONNX Layer	Image Processing Toolbox™
DepthToSpace	depthToSpace2dLayer (Image Processing Toolbox)
Resize	resize2dLayer (Image Processing Toolbox) or resize3dLayer (Image Processing Toolbox)
SpaceToDepth	spaceToDepthLayer (Image Processing Toolbox)
Upsample	resize2dLayer (Image Processing Toolbox) or resize3dLayer (Image Processing Toolbox)

Tips

• If the ONNX network contains a layer that Deep Learning Toolbox Converter for ONNX Model Format does not support (see Supported ONNX Layers), then importONNXNetwork returns an error message. In this case, you can still use importONNXLayers to import the network architecture and weights.

• You can import an ONNX network with multiple inputs and a single output using importONNXNetwork. If the network has multiple outputs, use importONNXLayers. The importONNXLayers function inserts placeholder layers for the outputs. After importing, you can find and replace the placeholder layers by using findPlaceholderLayers and replaceLayer, respectively. For an example, see Import and Assemble ONNX Network with Multiple Outputs. To learn about a deep learning network with multiple inputs and multiple outputs, see Multiple-Input and Multiple-Output Networks.

• To use a pretrained network for prediction or transfer learning on new images, you must preprocess your images in the same way the images that were used to train the imported model were preprocessed. The most common preprocessing steps are resizing images, subtracting image average values, and converting the images from BGR images to RGB.

  • To resize images, use imresize. For example, imresize(image,[227,227,3]).

  • To convert images from RGB to BGR format, use flip. For example, flip(image,3).

  For more information on preprocessing images for training and prediction, see Preprocess Images for Deep Learning.

Compatibility Considerations

'ClassNames' option will be removed

Not recommended starting in R2018b

'ClassNames' will be removed. Use 'Classes' instead. To update your code, replace all instances of 'ClassNames' with 'Classes'. There are some differences between the corresponding properties in classification output layers that require additional updates to your code.

The ClassNames property of a classification output layer is a cell array of character vectors. The Classes property is a categorical array. To use the value of Classes with functions that require cell array input, convert the classes using the cellstr function.

References

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

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