User Portlet
| Discussions |
|---|
| When I am training a DNN (Deep Neural Network) a typical command is: NetTrain[trainCNN4a1, TrainSet, {"TrainedNet", "LossEvolutionPlot", "RMSWeightEvolutionPlot", "RMSGradientEvolutionPlot", "TotalTrainingTime",... |
| Over the last week I have been training a deep learning NN (VGG style). Overall the results look good, but the discontinuities between training sessions worry me. Here is the Validation loss graph: ![Training over 20 epochs with 4 different... |
| After having creating a number of CNN (Convolution Neural Networks) with NetTrain, I have constantly found the Error Loss per Epoch to be small but useful in the training panel when it is training, but the "LossEvolutionPlot" provided as an output to... |
| For all my computations today I get a message: "This computation has exceeded the memory limit for your plan" (see attachment) I can not even add 2+2. Any idea what is happening? ![enter image description here][1] [1]:... |
| Is anyone interested in and actively using Wolfram to do Deep Learning research? I am doing research in all areas of Deep Learning with my focus currently on VGG style of convolution neural networks (CNN). I will be branching out very soon to RLN,... |