Closed samkeene closed 8 years ago
I can not re-create this. It seems to work fine for me. If you train a NN like above, I think you should be able to do something like:
nn.actionCell{1}.nn
and see the "b" field in that structure....
What version of MATLAB / NNET toolbox? This was developed in 2012B, and runs fine on 2013.
Maybe it's a version problem?
I just updated both PRT and the deep learning toolbox, and I still get the same error. MATLAB version is:
version
ans =
7.14.0.739 (R2012a)
This classifier no longer exists in the PRT. In fact, the associated toolbox is deprecated: https://github.com/rasmusbergpalm/DeepLearnToolbox
Problem solved!
Recently updated, tried:
ds = prtDataGenMnist; nn = prtClassRasmusbergpalmDeepLearningNn + prtDecisionMap; yOut = nn.kfolds(ds,2);
Eventually got this error:
epoch 100/100. Took 0.47235 seconds. Mean squared error on training set is 0.26585 ??? Reference to non-existent field 'b'.
Error in ==> prtClassRasmusbergpalmDeepLearningNn>prtClassRasmusbergpalmDeepLearningNn.runAction at 74 tempY = zeros(size(dataSet.X,1),size(self.nn.b{end},1));
Error in ==> prtAction>prtAction.runActionOnTrainingData at 570 dsOut = runAction(self, dsIn);
Error in ==> prtAction>prtAction.runOnTrainingData at 182 dsOut = runActionOnTrainingData(self, dsOut);
Error in ==> prtAlgorithm>prtAlgorithm.trainAction at 309 input{topoOrder(i)} = runOnTrainingData(Obj.actionCell{topoOrder(i-1)},currentInput);
Error in ==> prtAction>prtAction.train at 217 self = trainAction(self, ds);
Error in ==> prtAction>prtAction.crossValidate at 359 trainedAction = self.train(trainDs);
Error in ==> prtAction>prtAction.kfolds at 431 [outputs{:}] = self.crossValidate(ds,keys);