I am trying to customize an example of VDSR. Prepared the setup according to the receipe and the training works nicely. However, I am trying to combine it with custom training loop as in the example NN with multiple outputs (just using SGDM optimizer). The problem is that it fails during the evaluation of NN with the data from data store/minibatch queue.
K>> [Y] = predict(net, X);
Error using DAGNetwork/predict
Invalid 2-D image data. Specify image data as a 3-D numeric array
containing a single image, a 4-D numeric array containing multiple
images, a datastore, or a table containing image file paths or images in
Something is strange about the NN input data here.
Following my understanding of the deepNN infrastructure I also tested it with synthetic data with similar result:
>> XX = dlarray(rand([41 41 1 1],'single'),'SSCB');
>> [Y] = predict(net,XX);
Error using DAGNetwork/predict
Invalid 2-D image data. Specify image data as a 3-D numeric array
containing a single image, a 4-D numeric array containing multiple
images, a datastore, or a table containing image file paths or images in
the first column.
Error in SeriesNetwork/predict (line 320)
Built in train function works with the data, however how it delas with it is hard to get, Tried to debug it but is is difficult for so much object oriented code :(. I believe it has smth to do with randomPatchExtractionDatastore).
Any help would be appreciated.
Przemek
The loop looks like this (the rst is identical to the example):
mbq = minibatchqueue(dsTrain);
numObservationsTrain = dsTrain.NumObservations;
numIterationsPerEpoch = ceil(numObservationsTrain / miniBatchSize);
numIterations = numEpochs * numIterationsPerEpoch;
monitor = trainingProgressMonitor(Metrics="Loss",Info=["Epoch","LearnRate"],XLabel="Iteration");
while epoch < numEpochs && ~monitor.Stop
while hasdata(mbq) && ~monitor.Stop
iteration = iteration + 1;
[loss,gradients] = dlfeval(@modelLoss,net,X,T);
learnRate = initialLearnRate/(1 + decay*iteration);
[net,velocity] = sgdmupdate(net,gradients,velocity,learnRate,momentum);
recordMetrics(monitor,iteration,Loss=loss);
updateInfo(monitor,Epoch=epoch,LearnRate=learnRate);
monitor.Progress = 100 * iteration/numIterations;
function [loss,gradients] = modelLoss(net,X,T)
gradients = dlgradient(loss,net.Learnables);
