Architecture of convolutional autoencoders in Matlab 2019b

Question

Alberto Tellaeche 2020-3-18

2
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/511522-architecture-of-convolutional-autoencoders-in-matlab-2019b

评论： Jian Wang 2021-5-29

采纳的回答： Mahesh Taparia

Hello all,

I am very interested in training convolutional autoencoders in MATLAB 2019b.

I have found the instruction trainAutoencoder, but it does not allow to specify the convolutional layers architecture.

I want to design my autoencoder using Deep Network Designer tool, and then train it just as it is done with CNNs, FasterRCNN algorithms, etc, using my image dataset.

Is this possible? Is there any code oxample out there to do so?

Thank you all in advance,

Best,

Alberto

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Mahesh Taparia 2020-3-23

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/511522-architecture-of-convolutional-autoencoders-in-matlab-2019b#answer_421445

在 MATLAB Online 中打开

Hi

You can define custom architecture of auoencoder using deep learning layers. You can refer to this documentation for the list of deep learning layers supported in MATLAB. For example, the autoencoder network can be defined as:

layers=[
    imageInputLayer(size,"Name","imageinput",'Normalization','none')  %size is the size of input
    fullyConnectedLayer(9*R,"Name","fc_1")    %R can be any number/ factor
    leakyReluLayer(0.01,"Name","leakyrelu_1")
    fullyConnectedLayer(6*R,"Name","fc_2")
    leakyReluLayer(0.01,"Name","leakyrelu_3")
    fullyConnectedLayer(3*R,"Name","fc_3")
    leakyReluLayer(0.01,"Name","leakyrelu_4")
    fullyConnectedLayer(R,"Name","fc_4")
    batchNormalizationLayer("Name","batchnorm")
    reluLayer('Name','relu1')
    dropoutLayer('Name','drop')
    fullyConnectedLayer(3*R,"Name","fc_4")
    leakyReluLayer(0.01,"Name","leakyrelu_5")
    fullyConnectedLayer(6*R,"Name","fc_4")
    leakyReluLayer(0.01,"Name","leakyrelu_6")
    fullyConnectedLayer(9*R,"Name","fc_4")
    leakyReluLayer(0.01,"Name","leakyrelu_7")
    fullyConnectedLayer(size,"Name","fc_5")
    leakyReluLayer(0.01,"Name","leakyrelu_8")
    regressionLayer("Name","regressionoutput")];

You can use 2D / 3D conv layer/ any other layer as per your architecture. After defining the network, you can train the model. For reference you can check this documentation for that.

For custom loss function, you can check this documentation.

Hope it will help!

3 个评论
显示 1更早的评论隐藏 1更早的评论

Mahesh Taparia 2020-10-17

Hi

You can replace the fully connected layer with convolution layer in the above code, then it will be a convolutional autoencoder. You can refer to this documentation of convolution layer for more details. You can change the layers as per your application.

Jian Wang 2021-5-29