Networks and Layers Supported for Code Generation

MATLAB^® Coder™ supports code generation for dlnetwork (Deep Learning Toolbox), series, and directed acyclic graph (DAG) networks. You can generate code for any trained neural network that uses supported deep learning networks, layers and classes.

Supported Pretrained Networks

These pretrained networks, available in Deep Learning Toolbox™, are supported for code generation. You can use imagePretrainedNetwork (Deep Learning Toolbox) function to load these pretrained neural networks as dlnetwork (Deep Learning Toolbox) objects for code generation. Note that code generation does not support setting the name-value argument Weights of imagePretrainedNetwork function to "none". For example, use this code to load a pretrained GoogLeNet neural network.

net = imagePretrainedNetwork("googlenet")

You can use analyzeNetworkForCodegen to see if a network is compatible for code generation for a specific deep learning library. For example:

result = analyzeNetworkForCodegen(imagePretrainedNetwork("googlenet"),TargetLibrary='none')

imagePretrainedNetwork Model Name Argument	Generic C/C++	Intel® MKL-DNN and ARM® Compute Libraries
"alexnet"
"darknet19"
"darknet53"
"densenet201"
"efficientnetb0"
"googlenet"
"inceptionresnetv2"
"inceptionv3"
"mobilenetv2"
"nasnetlarge"
"nasnetmobile"
"resnet18"
"resnet50"
"resnet101"
"shufflenet"		Note The ARM Compute library is not supported for shufflenet.
"squeezenet"
"vgg16"
"vgg19"
"xception"

Supported Layers

These layers are supported for code generation for the target deep learning libraries specified in the table.

Note

In the following tables, the information icon indicates that the network, layer, or class has limited code generation capabilities. You might see errors and unexpected behavior. For more information, see the Extended Capabilities section on the page for that network, layer, or class.

Input Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
imageInputLayer (Deep Learning Toolbox)
sequenceInputLayer (Deep Learning Toolbox)
featureInputLayer (Deep Learning Toolbox)

Convolution and Fully Connected Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
convolution1dLayer (Deep Learning Toolbox)
convolution2dLayer (Deep Learning Toolbox)
fullyConnectedLayer (Deep Learning Toolbox)
groupedConvolution2dLayer (Deep Learning Toolbox)	Note You can generate generic C/C++ code for channel-wise convolution when the number of groups is equal to the number of filter channels.
transposedConv2dLayer (Deep Learning Toolbox)

Sequence Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
bilstmLayer (Deep Learning Toolbox)
flattenLayer (Deep Learning Toolbox)
gruProjectedLayer (Deep Learning Toolbox)
gruLayer (Deep Learning Toolbox)
lstmLayer (Deep Learning Toolbox)
lstmProjectedLayer (Deep Learning Toolbox)
sequenceInputLayer (Deep Learning Toolbox)
wordEmbeddingLayer (Text Analytics Toolbox)

Activation Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
clippedReluLayer (Deep Learning Toolbox)
eluLayer (Deep Learning Toolbox)
gelu (Deep Learning Toolbox)
geluLayer (Deep Learning Toolbox)
leakyReluLayer (Deep Learning Toolbox)
preluLayer (Deep Learning Toolbox)
reluLayer (Deep Learning Toolbox)
sigmoidLayer (Deep Learning Toolbox)
softmaxLayer (Deep Learning Toolbox)
softplusLayer (Reinforcement Learning Toolbox)
swishLayer (Deep Learning Toolbox)
tanhLayer (Deep Learning Toolbox)

Normalization Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
batchNormalizationLayer (Deep Learning Toolbox)
crossChannelNormalizationLayer (Deep Learning Toolbox)
instanceNormalizationLayer (Deep Learning Toolbox)
layerNormalizationLayer (Deep Learning Toolbox)
groupNormalizationLayer (Deep Learning Toolbox)

Utility Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
crop2dLayer (Deep Learning Toolbox)
dropoutLayer (Deep Learning Toolbox)
scalingLayer (Reinforcement Learning Toolbox)
spatialDropoutLayer (Deep Learning Toolbox)

Resizing Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
resize2dLayer (Image Processing Toolbox)

Pooling and Unpooling Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
adaptiveAveragePooling2dLayer (Deep Learning Toolbox)
averagePooling1dLayer (Deep Learning Toolbox)
averagePooling2dLayer (Deep Learning Toolbox)
globalAveragePooling1dLayer (Deep Learning Toolbox)
globalAveragePooling2dLayer (Deep Learning Toolbox)
globalMaxPooling1dLayer (Deep Learning Toolbox)
globalMaxPooling2dLayer (Deep Learning Toolbox)
maxPooling1dLayer (Deep Learning Toolbox)
maxPooling2dLayer (Deep Learning Toolbox)
maxUnpooling2dLayer (Deep Learning Toolbox)		Note The ARM Compute library is not supported for maxUnpooling2dLayer.

Combination Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
additionLayer (Deep Learning Toolbox)
concatenationLayer (Deep Learning Toolbox)
depthConcatenationLayer (Deep Learning Toolbox)
multiplicationLayer (Deep Learning Toolbox)

Transformer Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
AttentionLayer (Deep Learning Toolbox)
embeddingConcatenationLayer (Deep Learning Toolbox)
indexing1dLayer (Deep Learning Toolbox)
patchEmbeddingLayer (Computer Vision Toolbox)
PositionEmbeddingLayer (Deep Learning Toolbox)
selfAttentionLayer (Deep Learning Toolbox)

Compute Vision and Image Processing Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
depthToSpace2dLayer (Image Processing Toolbox)
patchEmbeddingLayer (Computer Vision Toolbox)
spaceToDepthLayer (Image Processing Toolbox)
ssdMergeLayer (Computer Vision Toolbox)
resize2dLayer (Image Processing Toolbox)
yolov2TransformLayer (Computer Vision Toolbox)

Custom Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
Custom layers  More information Custom layers are layers, with or without learnable parameters, that you define for your problem. See: Define Custom Deep Learning Layers (Deep Learning Toolbox) Define Custom Deep Learning Layer for Code Generation (Deep Learning Toolbox) Networks and Layers Supported for Code Generation  Code generation limitations The outputs of the custom layer must be fixed-size arrays. Custom layers in sequence networks are supported for generic C/C++ code generation only. For code generation, custom layers must contain the %#codegen pragma. You can pass dlarray to custom layers if: The custom layer is in dlnetwork. Custom layer is in a DAG or series network and either inherits from nnet.layer.Formattable or has no backward propagation. For unsupported dlarray methods, then you must extract the underlying data from the dlarray, perform the computations and reconstruct the data back into the dlarray for code generation. For example, function Z = predict(layer, X) if coder.target('MATLAB') Z = doPredict(X); else if isdlarray(X) X1 = extractdata(X); Z1 = doPredict(X1); Z = dlarray(Z1); else Z = doPredict(X); end end end
Custom Output Layer (Deep Learning Toolbox)  More information An output layer including custom classification or regression output layers created by nnet.layer.ClassificationLayer or nnet.layer.RegressionLayer functions. For an example showing how to define a custom classification output layer and specify a loss function, see Define Custom Classification Output Layer (Deep Learning Toolbox). For an example showing how to define a custom regression output layer and specify a loss function, see Define Custom Regression Output Layer (Deep Learning Toolbox).

Custom Keras Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
nnet.keras.layer.ClipLayer (Deep Learning Toolbox)
nnet.keras.layer.FlattenCStyleLayer (Deep Learning Toolbox)
nnet.keras.layer.GlobalAveragePooling2dLayer (Deep Learning Toolbox)
nnet.keras.layer.PreluLayer (Deep Learning Toolbox)
nnet.keras.layer.SigmoidLayer (Deep Learning Toolbox)
nnet.keras.layer.TanhLayer (Deep Learning Toolbox)
nnet.keras.layer.TimeDistributedFlattenCStyleLayer (Deep Learning Toolbox)
nnet.keras.layer.ZeroPadding2dLayer (Deep Learning Toolbox)

Custom ONNX Layers

Layer	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
nnet.onnx.layer.ClipLayer (Deep Learning Toolbox)
nnet.onnx.layer.ElementwiseAffineLayer (Deep Learning Toolbox)
nnet.onnx.layer.FlattenInto2dLayer (Deep Learning Toolbox)
nnet.onnx.layer.FlattenLayer (Deep Learning Toolbox)
nnet.onnx.layer.GlobalAveragePooling2dLayer (Deep Learning Toolbox)
nnet.onnx.layer.IdentityLayer (Deep Learning Toolbox)
nnet.onnx.layer.PreluLayer (Deep Learning Toolbox)
nnet.onnx.layer.SigmoidLayer (Deep Learning Toolbox)
nnet.onnx.layer.TanhLayer (Deep Learning Toolbox)
nnet.onnx.layer.VerifyBatchSizeLayer (Deep Learning Toolbox)

Supported Classes

Class	Generic C/C++	Intel MKL-DNN and ARM Compute Libraries
dlnetwork (Deep Learning Toolbox)
DAGNetwork (Deep Learning Toolbox)
pointPillarsObjectDetector (Lidar Toolbox)
SeriesNetwork (Deep Learning Toolbox)
ssdObjectDetector (Computer Vision Toolbox)
yolov2ObjectDetector (Computer Vision Toolbox)
yolov3ObjectDetector (Computer Vision Toolbox)
yolov4ObjectDetector (Computer Vision Toolbox)
yoloxObjectDetector (Computer Vision Toolbox)