GAN Neural Network ( Project and Reshape Layer ) error.

Question

Zohaib Shehzad 2020-5-12

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/525002-gan-neural-network-project-and-reshape-layer-error

回答： Yonglei GUI 2021-2-21

I copied the code from the following path https://uk.mathworks.com/help/deeplearning/ug/train-generative-adversarial-network.html#TrainGenerativeAdversarialNetworkGANExample-7 and try to run it on Matlab 2019a version it give error on the varialbe projectandreshapelayer that it is undefined function and variable. Image is attached.

2 个评论
显示无隐藏无

Manal Allehyani 2020-9-21

i have same error , but my version r2020

did you solve it?

Alexander Hagg 2020-11-7

The projectAndReshapeLayer is a custom example that was provided to Matlab in one of the example. Open it using the following command and save it to your local project (or add it to your path).

edit(fullfile(matlabroot,'examples','nnet','main','projectAndReshapeLayer.m'))

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Yonglei GUI 2021-2-21

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/525002-gan-neural-network-project-and-reshape-layer-error#answer_629204

在 MATLAB Online 中打开

classdef projectAndReshapeLayer < nnet.layer.Layer
    properties
        % (Optional) Layer properties.
        OutputSize
    end
    properties (Learnable)
        % Layer learnable parameters.
        
        Weights
        Bias
    end
    
    methods
        function layer = projectAndReshapeLayer(outputSize, numChannels, name)
            % Create a projectAndReshapeLayer.
            
            % Set layer name.
            layer.Name = name;
            % Set layer description.
            layer.Description = "Project and reshape layer with output size " + join(string(outputSize));
            
            % Set layer type.
            layer.Type = "Project and Reshape";
            
            % Set output size.
            layer.OutputSize = outputSize;
            
            % Initialize fully connect weights and bias.
            fcSize = prod(outputSize);
            layer.Weights = initializeGlorot(fcSize, numChannels);
            layer.Bias = zeros(fcSize, 1, 'single');
        end
        
        function Z = predict(layer, X)
            % Forward input data through the layer at prediction time and
            % output the result.
            %
            % Inputs:
            %         layer - Layer to forward propagate through
            %         X     - Input data, specified as a 1-by-1-by-C-by-N 
            %                 dlarray, where N is the mini-batch size.
            % Outputs:
            %         Z     - Output of layer forward function returned as 
            %                 an sz(1)-by-sz(2)-by-sz(3)-by-N dlarray,
            %                 where sz is the layer output size and N is
            %                 the mini-batch size.
            % Fully connect.
            weights = layer.Weights;
            bias = layer.Bias;
            X = fullyconnect(X,weights,bias,'DataFormat','SSCB');
            
            % Reshape.
            outputSize = layer.OutputSize;
            Z = reshape(X, outputSize(1), outputSize(2), outputSize(3), []);
        end
    end
end
function weights = initializeGlorot(numOut, numIn)
% Initialize weights using uniform Glorot.
varWeights = sqrt( 6 / (numIn + numOut) );
weights = varWeights * (2 * rand([numOut, numIn], 'single') - 1);
end