New answers tagged

1

Time to revitalize this question thanks to Mr. Aster Ctor with DeepDreamBeta and DeepDreamAlpha


5

The first point in the documentation for ElementwiseLayer contains a list of functions that can be used with it. Unfortunately it's a pretty limited list. You might have better luck writing a generator for noisy images and using that as a second input for your network, then doing an elementwise add of the noise and the image at some point in the network. ...


1

It depends on if you want the predicted probabilities for each "true" class or each "predicted" class. cm["Probabilities"] gives you the predicted probabilities associated with the "true" class (but, of course, by itself doesn't tell you what that true class is). cm[[1,2,2]] gets you the true status. cm[[1,3]] gets you the predicted status. Exp[cm[[1,...


2

Update - Address comment. They are actually identical, just different binning / range All classes cm["Probabilities"] // Histogram[#, {0.1}, PlotRange -> {{0., 1.}, {All, All}}] & cm["ProbabilityHistogram"] What is different is your result for cm["ProbabilityHistogram"]. Perhaps you specified a Method->? Here is one way to do it. train = ...


2

This video recording: ORLMLDS Deep learning series (2): "Using Keras with R (...and MXNet with WL)" uses both R and Mathematica (WL). It should be a good introduction to the typical functionalities provided by Neural Network libraries, and related rules of thumb and techniques. There is a dedicated GitHub repository: MathematicaVsR -- Deep Learning ...


Top 50 recent answers are included