Documentation

AlexNet convolutional neural network. For the pretrained AlexNet model, see alexnet (Deep Learning Toolbox).

DenseNet-201 convolutional neural network. For the pretrained DenseNet-201 model, see densenet201 (Deep Learning Toolbox).

EfficientNet-b0 convolutional neural network. For the pretrained EfficientNet-b0 model, see efficientnetb0 (Deep Learning Toolbox).

GoogLeNet convolutional neural network. For the pretrained GoogLeNet model, see googlenet (Deep Learning Toolbox).

Inception-ResNet-v2 convolutional neural network. For the pretrained Inception-ResNet-v2 model, see inceptionresnetv2 (Deep Learning Toolbox).

MobileNet-v2 convolutional neural network. For the pretrained MobileNet-v2 model, see mobilenetv2 (Deep Learning Toolbox).

NASNet-Large convolutional neural network. For the pretrained NASNet-Large model, see nasnetlarge (Deep Learning Toolbox).

NASNet-Mobile convolutional neural network. For the pretrained NASNet-Mobile model, see nasnetmobile (Deep Learning Toolbox).

ResNet-18, ResNet-50, and ResNet-101 convolutional neural networks. For the pretrained ResNet models, see resnet18 (Deep Learning Toolbox), resnet50 (Deep Learning Toolbox), and resnet101 (Deep Learning Toolbox).

Multi-class pixelwise segmentation network. For more information, see segnetLayers (Computer Vision Toolbox).

Small, deep neural network. For the pretrained SqeezeNet models, see squeezenet (Deep Learning Toolbox).

VGG-16 convolutional neural network. For the pretrained VGG-16 model, see vgg16 (Deep Learning Toolbox).

VGG-19 convolutional neural network. For the pretrained VGG-19 model, see vgg19 (Deep Learning Toolbox).

Xception convolutional neural network. For the pretrained Xception model, see xception (Deep Learning Toolbox).

Addition layer

Anchor box layer

Average pooling layer

Batch normalization layer

Create classification output layer

Clipped Rectified Linear Unit (ReLU) layer

Concatenation layer

2-D convolution layer

Yes

Layer that applies 2-D cropping to the input

Channel-wise local response normalization layer

Custom layers

Custom layers, with or without learnable parameters, that you define for your problem.

See:

The outputs of the custom layer must be fixed-size arrays.

Custom layers in sequence networks are not supported for code generation.

Yes

Custom output layers

All output layers including custom classification or regression output layers created by using nnet.layer.ClassificationLayer or nnet.layer.RegressionLayer.

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).

Yes

Yes

Depth concatenation layer

Yes

A Dice pixel classification layer provides a categorical label for each image pixel or voxel using generalized Dice loss.

Dropout layer

Exponential linear unit (ELU) layer

Fully connected layer

Global average pooling layer for spatial data

Yes

Yes

2-D global max pooling layer

groupedConvolution2dLayer (Deep Learning Toolbox)

2-D grouped convolutional layer

Yes

Yes

gruLayer (Deep Learning Toolbox)

Gated recurrent unit (GRU) layer

Yes

Yes

Image input layer

Leaky Rectified Linear Unit (ReLU) layer

Long short-term memory (LSTM) layer

Max pooling layer

Max unpooling layer

Multiplication layer

Create pixel classification layer for semantic segmentation

Box regression layer for Fast and Faster R-CNN

Classification layer for region proposal networks (RPNs)

Create a regression output layer

Rectified Linear Unit (ReLU) layer

Sequence input layer

Softmax layer

Yes

Softplus layer for actor or critic network

Space to depth layer

SSD merge layer for object detection

nnet.keras.layer.FlattenCStyleLayer

Flattens activations into 1-D assuming C-style (row-major) order

Yes

Yes

Global average pooling layer for spatial data

Yes

Yes

nnet.keras.layer.SigmoidLayer

Sigmoid activation layer

Yes

Yes

nnet.keras.layer.TanhLayer

Hyperbolic tangent activation layer

Yes

Yes

nnet.keras.layer.ZeroPadding2dLayer

Zero padding layer for 2-D input

Yes

Yes

Layer that performs element-wise scaling of the input followed by an addition

nnet.onnx.layer.FlattenLayer

Flatten layer for ONNX™ network

Yes

Yes

nnet.onnx.layer.IdentityLayer

Layer that implements ONNX identity operator

Yes

Yes

tanhLayer (Deep Learning Toolbox)

Hyperbolic tangent (tanh) layer

Yes

Yes

transposedConv2dLayer (Deep Learning Toolbox)

Transposed 2-D convolution layer

Code generation does not support asymmetric cropping of the input. For example, specifying a vector [t b l r] for the 'Cropping' parameter to crop the top, bottom, left, and right of the input is not supported.

Yes

Yes

wordEmbeddingLayer (Text Analytics Toolbox)

A word embedding layer maps word indices to vectors

Yes

Yes

yolov2OutputLayer (Computer Vision Toolbox)

Output layer for YOLO v2 object detection network

Yes

Yes

yolov2ReorgLayer (Computer Vision Toolbox)

Reorganization layer for YOLO v2 object detection network

Yes

Yes

yolov2TransformLayer (Computer Vision Toolbox)

Transform layer for YOLO v2 object detection network

Yes

Yes

yolov2ObjectDetector (Computer Vision Toolbox)

Yes

Yes

Object to detect objects using the SSD-based detector.

Yes

Yes