Layer - Network layer for deep learning - MATLAB (original) (raw)

• Documentation
• Examples
• Functions
• Blocks
• Apps
• Videos
• Answers

Main Content

Network layer for deep learning

Description

Layers that define the architecture of neural networks for deep learning.

Examples

collapse all

Construct Network Architecture

Define a convolutional neural network architecture for classification with one convolutional layer, a ReLU layer, and a fully connected layer.

layers = [ ... imageInputLayer([28 28 3]) convolution2dLayer([5 5],10) reluLayer fullyConnectedLayer(10) softmaxLayer classificationLayer]

layers = 6x1 Layer array with layers:

 1   ''   Image Input             28x28x3 images with 'zerocenter' normalization
 2   ''   2-D Convolution         10 5x5 convolutions with stride [1  1] and padding [0  0  0  0]
 3   ''   ReLU                    ReLU
 4   ''   Fully Connected         10 fully connected layer
 5   ''   Softmax                 softmax
 6   ''   Classification Output   crossentropyex

layers is a Layer object.

Alternatively, you can create the layers individually and then concatenate them.

input = imageInputLayer([28 28 3]); conv = convolution2dLayer([5 5],10); relu = reluLayer; fc = fullyConnectedLayer(10); sm = softmaxLayer; co = classificationLayer;

layers = [ ... input conv relu fc sm co]

layers = 6x1 Layer array with layers:

 1   ''   Image Input             28x28x3 images with 'zerocenter' normalization
 2   ''   2-D Convolution         10 5x5 convolutions with stride [1  1] and padding [0  0  0  0]
 3   ''   ReLU                    ReLU
 4   ''   Fully Connected         10 fully connected layer
 5   ''   Softmax                 softmax
 6   ''   Classification Output   crossentropyex

Access Layers and Properties in Layer Array

Define a convolutional neural network architecture for classification with one convolutional layer, a ReLU layer, and a fully connected layer.

layers = [ ... imageInputLayer([28 28 3]) convolution2dLayer([5 5],10) reluLayer fullyConnectedLayer(10) softmaxLayer];

Display the image input layer by selecting the first layer.

ans = ImageInputLayer with properties:

                  Name: ''
             InputSize: [28 28 3]
    SplitComplexInputs: 0

Hyperparameters DataAugmentation: 'none' Normalization: 'zerocenter' NormalizationDimension: 'auto' Mean: []

View the input size of the image input layer.

Display the stride for the convolutional layer.

Access the bias learn rate factor for the fully connected layer.

layers(4).BiasLearnRateFactor

Version History

Introduced in R2016a