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

cnnnetworktrain

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.

Best Answer

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

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

Related Solutions

MATLAB: How to change color model of all pictures in image datastore

I hope I've figured this problem with Transform datastore:

First error

Error using trainNetwork (line 170)
Invalid transform function defined on datastore.
Error in transferlearning (line 37)
CNN = trainNetwork(dsnew.train, lgraph, opts);
Caused by:
    Error using nnet.internal.cnn.util.NetworkDataValidator/assertDatastoreHasResponses (line 140)
    Invalid transform function defined on datastore.
        Error using rgb2hsv>parseInputs (line 95)
        MAP must be a Mx3 array.

was figured out by using im2uint8 function.

im2uint8(rgb2hsv(dataIn));

Second error

Error using trainNetwork (line 170)
Invalid training data. Responses must be nonempty.

was figured out thanks to this script in transformFcn file:

function dataOut = transformFcn(dataIn)
B = table2cell(dataIn);
NoImg = size(B,1);
for i=1:NoImg
    B{i,1} = im2uint8(rgb2hsv(B{i,1}));
end
dataOut = cell2table(B);
end

In main file:

imds.train = imageDatastore(fullfile(trainDirectoryName, categories), 'LabelSource', 'foldernames');
imds.train = splitEachLabel(imds.train,5, 'randomize');
auimds.train = augmentedImageDatastore(sizeImg, imds.train);
dsnew.train = transform(auimds.train, @transformFcn);
dsnew.train.UnderlyingDatastore.MiniBatchSize = 10;

ReadFcn takes only one image, instead Transform datastore takes whole batch of images (size of this batch is defined in the last line: dsnew.train.UnderlyingDatastore.MiniBatchSize; default is 128).

Hope this helps :-)

MATLAB: Using fft to replace feature learning in CNN

Hi,

I understand that you are using FFT for feature learning instead of CNN and the accuracy is staying at 10%. This is due to the use of reluLayer before the softmaxLayer in the layer before classificationLayer. You can use the following layer definition, to improve the training results.

layers = [
    featureInputLayer(28*28*2)
    fullyConnectedLayer(28*28)
    reluLayer
    fullyConnectedLayer(10)
    softmaxLayer
    classificationLayer];

For more information, refer the Define Network Architecture section in this example.

Best Answer

Related Solutions

MATLAB: How to change color model of all pictures in image datastore

MATLAB: Using fft to replace feature learning in CNN

Related Question