help with defining neural networks

Question

Radians 2020-2-10

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/504628-help-with-defining-neural-networks

评论： Radians 2020-2-19

采纳的回答： Jyothis Gireesh

在 MATLAB Online 中打开

Hi,

When I define the following layers:

decodingLayers_2=[ ...
    createUpsampleTransponseConvLayer(2,8), ...
    reluLayer, ...
    convolution2dLayer(3,1,'Padding','same'), ...
    clippedReluLayer(1.0), ...
    %clippedReluLayer(1.0), ...
    regressionLayer];

Matlab gives the following error:

Error using vertcat

Dimensions of arrays being concatenated are not consistent.

But when I modify the above just a bit as follows:

decodingLayers_2=[ ...
    createUpsampleTransponseConvLayer(2,8), ...
    reluLayer, ...
    convolution2dLayer(3,1,'Padding','same'), ...
    clippedReluLayer(1.0), ...
    clippedReluLayer(1.0), ...
    regressionLayer];

The error disappears.

Please let me know why is this happening and why do I need to put 2 relu layers at the end when I just need 1.

thanks

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

Jyothis Gireesh 2020-2-13

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/504628-help-with-defining-neural-networks#answer_415354

在 MATLAB Online 中打开

This error message may be due to the presence of a comment inside the “decodingLayers_2” array. This may interfere with the line continuation operator and eventually lead to an error during run-time.

One way to avoid this is to avoid commenting inside the array definition. So, the updated code can be as follows

decodingLayers_2 = [ ...
    createUpsampleTransponseConvLayer(2,8), ...
    reluLayer, ...
    convolution2dLayer(3,1,'Padding','same'), ...
    clippedReluLayer(1.0), ...
    regressionLayer];