Problem with convolutionUnit function

Question

Hind Haboubi 2021-4-20

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/807497-problem-with-convolutionunit-function

评论： Hind Haboubi ，2021-4-23

采纳的回答： Abhishek Gupta ，

Hello everyone, i wanted to creat a resnet 50 but i get this error:

Unrecognized function or variable

'convolutionalUnit'.

What should i do please?

netWidth = 16;
layers = [
    imageInputLayer([224 224 3],'Name','input')
    
    convolution2dLayer(3,netWidth,'Padding','same','Name','convInp')
    
    batchNormalizationLayer('Name','BNInp')
    
    reluLayer('Name','reluInp')
   
    convolutionalUnit(netWidth,1,'S1U1')
    additionLayer(2,'Name','add11')
    reluLayer('Name','relu11')
    convolutionalUnit(netWidth,1,'S1U2')
    additionLayer(2,'Name','add12')
    reluLayer('Name','relu12')
    
    convolutionalUnit(2*netWidth,2,'S2U1')
    additionLayer(2,'Name','add21')
    reluLayer('Name','relu21')
    convolutionalUnit(2*netWidth,1,'S2U2')
    additionLayer(2,'Name','add22')
    reluLayer('Name','relu22')
    
    convolutionalUnit(4*netWidth,2,'S3U1')
    additionLayer(2,'Name','add31')
    reluLayer('Name','relu31')
    convolutionalUnit(4*netWidth,1,'S3U2')
    additionLayer(2,'Name','add32')
    reluLayer('Name','relu32')
    
    averagePooling2dLayer(8,'Name','globalPool')
    
    fullyConnectedLayer(2,'Name','fcFinal')
    
    softmaxLayer('Name','softmax')
    
    classificationLayer('Name','classoutput')
    ];
    

0 个评论
显示 -1更早的评论隐藏 -1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

Abhishek Gupta 2021-4-23

2
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/807497-problem-with-convolutionunit-function#answer_682435

编辑：Abhishek Gupta 2021-4-23

Hi,

You are getting this error because MATLAB doesn't recognize the 'convolutionalUnit' as the name of a function on the MATLAB path (see this for more details related to the error message). You can resolve this issue by adding the 'convolutionalUnit' function in your MATLAB path. You can find the code for this function in the documentation link below (just above the references section):-

Train Residual Network for Image Classification

For your convenience, I am also copy-pasting the code here: -

function layers = convolutionalUnit(numF,stride,tag)
layers = [
    convolution2dLayer(3,numF,'Padding','same','Stride',stride,'Name',[tag,'conv1'])
    batchNormalizationLayer('Name',[tag,'BN1'])
    reluLayer('Name',[tag,'relu1'])
    convolution2dLayer(3,numF,'Padding','same','Name',[tag,'conv2'])
    batchNormalizationLayer('Name',[tag,'BN2'])];
end