Main Content

Supported Networks, Layers, and Classes

GPU Coder™ supports code generation for series and directed acyclic graph (DAG) neural networks. This page provides a list of supported deep learning networks, layers and classes.

Note that the code generator represents characters in an 8-bit ASCII codeset that the locale setting determines. Therefore, the use of non-ASCII characters in class names, layer names, layer description, or network names might result in errors. For more information, see Encoding of Characters in Code Generation.

Supported Pretrained Networks

You can train a neural network on either a CPU, a GPU, or multiple GPUs by using the Deep Learning Toolbox™ or use one of the pretrained networks listed in the table and generate CUDA® code.

These pretrained networks are supported for code generation by GPU Coder for these target deep learning libraries.

- Support can have limitations. You might see errors and unexpected behavior. For more information, see the extended capabilities section on the reference page.

Network NameCUDATensorRTcuDNN

alexnet (Deep Learning Toolbox)

Caffe Network

See importCaffeNetwork (Deep Learning Toolbox).

darknet19 (Deep Learning Toolbox)

darknet53 (Deep Learning Toolbox)

deeplabv3plusLayers (Computer Vision Toolbox)

densenet201 (Deep Learning Toolbox)

efficientnetb0 (Deep Learning Toolbox)

googlenet (Deep Learning Toolbox)

inceptionresnetv2 (Deep Learning Toolbox)

inceptionv3 (Deep Learning Toolbox)

mobilenetv2 (Deep Learning Toolbox)

nasnetlarge (Deep Learning Toolbox)

nasnetmobile (Deep Learning Toolbox)

resnet18 (Deep Learning Toolbox)

resnet50 (Deep Learning Toolbox)

resnet101 (Deep Learning Toolbox)

segnetLayers (Computer Vision Toolbox)

squeezenet (Deep Learning Toolbox)

vgg16 (Deep Learning Toolbox)

vgg19 (Deep Learning Toolbox)

xception (Deep Learning Toolbox)

yolov2Layers (Computer Vision Toolbox)

Supported Layers

These layers are supported for code generation by GPU Coder for these target deep learning libraries.

Input Layers

Layer NameCUDATensorRTcuDNN

imageInputLayer (Deep Learning Toolbox)

sequenceInputLayer (Deep Learning Toolbox)

featureInputLayer (Deep Learning Toolbox)

Convolution and Fully Connected Layers

Layer NameCUDATensorRTcuDNN

convolution1dLayer (Deep Learning Toolbox)

  

convolution2dLayer (Deep Learning Toolbox)

fullyConnectedLayer (Deep Learning Toolbox)

groupedConvolution2dLayer (Deep Learning Toolbox)

 

transposedConv2dLayer (Deep Learning Toolbox)

 

Sequence Layers

Layer NameCUDATensorRTcuDNN

sequenceInputLayer (Deep Learning Toolbox)

bilstmLayer (Deep Learning Toolbox)

flattenLayer (Deep Learning Toolbox)

 

gruLayer (Deep Learning Toolbox)

lstmLayer (Deep Learning Toolbox)

sequenceFoldingLayer (Deep Learning Toolbox)

  

sequenceUnfoldingLayer (Deep Learning Toolbox)

  

wordEmbeddingLayer (Text Analytics Toolbox)

Activation Layers

Layer NameCUDATensorRTcuDNN

clippedReluLayer (Deep Learning Toolbox)

eluLayer (Deep Learning Toolbox)

leakyReluLayer (Deep Learning Toolbox)

reluLayer (Deep Learning Toolbox)

gelu (Deep Learning Toolbox)

softplusLayer (Reinforcement Learning Toolbox)

swishLayer (Deep Learning Toolbox)

tanhLayer (Deep Learning Toolbox)

Normalization, Dropout, and Cropping Layers

Layer NameCUDATensorRTcuDNN

batchNormalizationLayer (Deep Learning Toolbox)

crossChannelNormalizationLayer (Deep Learning Toolbox)

 

groupNormalizationLayer (Deep Learning Toolbox)

layerNormalizationLayer (Deep Learning Toolbox)

crop2dLayer (Deep Learning Toolbox)

 

dropoutLayer (Deep Learning Toolbox)

scalingLayer (Reinforcement Learning Toolbox)

Pooling and Unpooling Layers

Layer NameCUDATensorRTcuDNN

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)

 

Combination Layers

Layer NameCUDATensorRTcuDNN

additionLayer (Deep Learning Toolbox)

concatenationLayer (Deep Learning Toolbox)

depthConcatenationLayer (Deep Learning Toolbox)

Transformer Layers

Layer NameCUDATensorRTcuDNN

AttentionLayer (Deep Learning Toolbox)

  

embeddingConcatenationLayer (Deep Learning Toolbox)

  

indexing1dLayer (Deep Learning Toolbox)

  

patchEmbeddingLayer (Computer Vision Toolbox)

  

PositionEmbeddingLayer (Deep Learning Toolbox)

  

selfAttentionLayer (Deep Learning Toolbox)

  

Object Detection Layers

Layer NameCUDATensorRTcuDNN

anchorBoxLayer (Computer Vision Toolbox)

depthToSpace2dLayer (Image Processing Toolbox)

spaceToDepthLayer (Image Processing Toolbox)

 

ssdMergeLayer (Computer Vision Toolbox)

yolov2TransformLayer (Computer Vision Toolbox)

 

rcnnBoxRegressionLayer (Computer Vision Toolbox)

focalLossLayer (Computer Vision Toolbox)

rpnClassificationLayer (Computer Vision Toolbox)

 

yolov2OutputLayer (Computer Vision Toolbox)

 

Output Layers

Layer NameCUDATensorRTcuDNN

classificationLayer (Deep Learning Toolbox)

dicePixelClassificationLayer (Computer Vision Toolbox)

 

focalLossLayer (Computer Vision Toolbox)

pixelClassificationLayer (Computer Vision Toolbox)

 

rcnnBoxRegressionLayer (Computer Vision Toolbox)

regressionLayer (Deep Learning Toolbox)

rpnClassificationLayer (Computer Vision Toolbox)

 

sigmoidLayer (Deep Learning Toolbox)

softmaxLayer (Deep Learning Toolbox)

Custom Output Layer (Deep Learning Toolbox)

 More information

Custom Keras Layers

Layer NameCUDATensorRTcuDNN

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 NameCUDATensorRTcuDNN

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)

Custom Layers

Layer NameCUDATensorRTcuDNN

Custom layers

 More information

 Code generation Limitations

Supported Classes

These classes are supported for code generation by GPU Coder for these target deep learning libraries.

NameCUDATensorRTcuDNN

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)

See Also

Functions

Objects

Related Topics