Variable changes unwantedly during repeated run

9 次查看（过去 30 天）

Gianluca Fuwa 2021-5-21

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/836378-variable-changes-unwantedly-during-repeated-run

评论： Gianluca Fuwa 2021-5-24

Hello,

I am currently trying to build a custom Neural Network using the Deep Network Designer and was getting an error message for one of my custom layers.

In said layer I want to multiply its input + bias with the weight matrix, but for some reason after a couple cycles the input vector changes its size so that the product can't be calculated.

The layer is the following

classdef weightedAdditionLayer < nnet.layer.Layer
    % Example custom weighted addition layer.
    properties
        inputsize
        outputsize
    end    
    
    properties (Learnable)
        Weights
    end
    
    methods
        function layer = weightedAdditionLayer(a,b,name) 
            % Set layer name.
            layer.Name = name;
            % Set layer description.
            layer.Description = "Weighted addition of inputs";
            
            layer.inputsize = a;
            layer.outputsize = b;
        
            % Initialize layer weights.
            layer.Weights = rand(layer.inputsize,layer.outputsize); 
        end
        
        function Z = predict(layer, X)
            Z = layer.Weights.' * [1;X(:)];
        end
    end
end

The vector that changes size is [1;X(:)], which goes from the wanted (201 x 1) to (12513 x 1) after approx. 6 cycles every time.

Could there be any reason in and/or outside of the code that causes this behaviour?

4 个评论
显示 2更早的评论隐藏 2更早的评论

Tarunbir Gambhir 2021-5-24

Can you try training your network using a dlarray with correct data format. You can convert your training data to dlarray and specify the data format, then use this dlarray for network training.

Gianluca Fuwa 2021-5-24

So, I figured out that the problem was the mini-batch size in my training options which caused an input to become size (98 x 1 x 1 x 128) because the mini batch size was 128.

After changing it to 1 everything worked fine.

请先登录，再进行评论。

请先登录，再回答此问题。

回答（0 个）

请先登录，再回答此问题。

类别

AI and Statistics Deep Learning Toolbox

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

产品

MATLAB

版本

R2021a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by