I'm using the same activations function (below), but I'm getting errors in MatLab 2017b in comparison to no errors in MatLab 2018a.
testFeatures = activations(myNetwork,semiImg,layer,'OutputAs', 'rows');
In my neural network semiImg is replaced by a augmentedDataSource object, whereas in my actual code where I run the network its a n by m by 3 matrix (representing an Image).
The thing is, in MatLab 2018a it works fine, but in MatLab 2017b it gives me an error (shows below).
Struct contents reference from a non-struct array object.Error in nnet.internal.cnn.layer.Layer>@(x)x.Name (line 161) layerNames = cellfun(@(x)x.Name, layers, 'UniformOutput', false);Error in nnet.internal.cnn.layer.Layer.getLayerNames (line 161) layerNames = cellfun(@(x)x.Name, layers, 'UniformOutput', false);Error in nnet.internal.cnn.layer.Layer.findLayerByName (line 156) layerNames = nnet.internal.cnn.layer.Layer.getLayerNames(layers);Error in nnet.internal.cnn.util.validateNetworkLayerNameOrIndex (line 11) [layerIndex, layerNames] = nnet.internal.cnn.layer.Layer.findLayerByName(internalLayers, name);Error in SeriesNetwork/activations (line 747) layerID = nnet.internal.cnn.util.validateNetworkLayerNameOrIndex(layerID, internalLayers, 'activations');Error in Segmentation (line 221) testColourFeatures = activations(myNetwork,semiImg,layer,'OutputAs', 'rows');
Best Answer