Message Boards Message Boards

Avoid error in ImageAugmentationLayer usage?

GROUPS:

This code fails with "NetTrain::interr: An internal error occurred. Please contact Wolfram Research. " Any ideas?

lnet = NetChain[
   {
    ImageAugmentationLayer[{115, 115}, 
     "ReflectionProbabilities" -> {0.5, 0.5}],
    LinearLayer[1788],
    LogisticSigmoid,
    LinearLayer[1788],
    2,
    SoftmaxLayer[]},
   "Output" -> NetDecoder[{"Class", {1, 2}}],
   "Input" -> NetEncoder[{"Image", {125, 125}}]
   ] ;

tSet = Table[
  RandomChoice[{RegionImage[Annulus[], RasterSize -> 125] -> "A", 
    RegionImage[Circle[], RasterSize -> 125] -> "C"}], 10] 

NetTrain[lnet, tSet]
POSTED BY: Jeff Burns
Answer
7 months ago

This is definitely a bug. Thanks for reporting it! Will be fixed for 11.3.

Answer
7 months ago

Group Abstract Group Abstract