Invalid training data. Responses must be nonempty when using networkTrain on CNN

1 次查看（过去 30 天）

Carlos Ramirez 2020-9-3

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/588652-invalid-training-data-responses-must-be-nonempty-when-using-networktrain-on-cnn

评论： JAYANTHI BALASUBRAMANIAN 2021-7-9

Hello,

I'm having issues with the transform of an ImageDatastore when is used as input to the networkTrain method. If I use the original ImageDatastore as input to the networkTrain, everything works as a charm. By using the read method on the transformed datastore and visualizing the images with imshow() I can see that the transform function is doing what is supposed to do (i.e., adding noise to the images in the ImageDatastore). However, when passing the TransformedDatastore to the networkTrain, the following message is thrown:

Error using trainNetwork (line 170)

Invalid training data. Responses must be nonempty.

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。

采纳的回答

Mohammad Sami 2020-9-4

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/588652-invalid-training-data-responses-must-be-nonempty-when-using-networktrain-on-cnn#answer_489667

If you have image processing toolbox, you may perhaps use denoisingImageDatastore

https://www.mathworks.com/help/releases/R2020a/images/ref/denoisingimagedatastore.html

9 个评论
显示 7更早的评论隐藏 7更早的评论

Carlos Ramirez 2020-9-4

编辑：Carlos Ramirez 2020-9-5

在 MATLAB Online 中打开

Sami, the transformed data store does not have a Labels property. I believe it relies on the labels stored in the UnderlyingDatastore. I borrowed a simple example from the Matlab help to reproduce the problem. Here it is:

digitDatasetPath = fullfile(matlabroot,'toolbox','nnet', ...
    'nndemos','nndatasets','DigitDataset');
imds = imageDatastore(digitDatasetPath, ...
    'IncludeSubfolders',true, ...
    'LabelSource','foldernames');
numTrainingFiles = 750;
[imdsTrain,imdsTest] = splitEachLabel(imds,numTrainingFiles,'randomize');
layers = [ ...
    imageInputLayer([28 28 1])
    convolution2dLayer(5,20)
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    fullyConnectedLayer(10)
    softmaxLayer
    classificationLayer];
options = trainingOptions('sgdm', ...
    'MaxEpochs',20,...
    'InitialLearnRate',1e-4, ...
    'Verbose',false, ...
    'Plots','training-progress');
idmsNew = transform(imds,@transformFcn);
net = trainNetwork(idmsNew,layers,options);
function [dataOut]= transformFcn(dataIn)
    Gray=dataIn;
    %Gray=Gray+20; // do whatever transformation you want to do here
    dataOut=Gray;
end

which results in:

Error using trainNetwork (line 170)

Invalid training data. Responses must be nonempty.

Error in test (line 28)

net = trainNetwork(idmsNew,layers,options);

drummer 2020-10-23

Great, it worked to me too.

Thanks.

I'm performing affine geometric transformation to volumetric images and MATLAB was also returning such error.

But only one thing I would like to ask to @Carlos is why you transformed all the imds?

Wasn't the purpose of your transformation to augment training data? This way, only imdsTrain would be applied the transformation...

I know there are several purposes to transform data. My question is just out of curiosity...

cheers

JAYANTHI BALASUBRAMANIAN 2021-7-9

hello,

I am also facing the same problem, but the transform function I used is for Image contrast enhancement for brightness preservation based on dynamic streatching.Can you suggest any methods to correct it

Thank You

请先登录，再进行评论。