image-data-pipeline tutorial not working

[plankes-projects]

Hello,

I am trying to implement a simple image recognition.
I followed the tutorial on http://deeplearning4j.org/image-data-pipeline und used the following LFW images as data
Training data: http://vis-www.cs.umass.edu/lfw/lfw-a.tgz

I attached my implementation. it should be exactly like the tutorial. But i get listed error.
Additionally the Evaluation class in this tutorial has the warning rawtypes.

Exception in thread "main" java.lang.IllegalArgumentException: Shapes do not match: x.shape=[10, 784], y.shape=[10, 432]
at org.nd4j.linalg.api.parallel.tasks.cpu.CPUTaskFactory.getTransformAction(CPUTaskFactory.java:92)
at org.nd4j.linalg.api.ops.executioner.DefaultOpExecutioner.doTransformOp(DefaultOpExecutioner.java:409)
at org.nd4j.linalg.api.ops.executioner.DefaultOpExecutioner.exec(DefaultOpExecutioner.java:62)
at org.nd4j.linalg.api.ndarray.BaseNDArray.subi(BaseNDArray.java:2660)
at org.nd4j.linalg.api.ndarray.BaseNDArray.subi(BaseNDArray.java:2641)
at org.nd4j.linalg.api.ndarray.BaseNDArray.sub(BaseNDArray.java:2419)
at org.deeplearning4j.nn.layers.BaseOutputLayer.getGradientsAndDelta(BaseOutputLayer.java:154)
at org.deeplearning4j.nn.layers.BaseOutputLayer.computeGradientAndScore(BaseOutputLayer.java:98)
at org.deeplearning4j.optimize.solvers.BaseOptimizer.gradientAndScore(BaseOptimizer.java:132)
at org.deeplearning4j.optimize.solvers.BaseOptimizer.optimize(BaseOptimizer.java:151)
at org.deeplearning4j.optimize.Solver.optimize(Solver.java:52)
at org.deeplearning4j.nn.layers.BaseOutputLayer.fit(BaseOutputLayer.java:363)
at org.deeplearning4j.nn.multilayer.MultiLayerNetwork.finetune(MultiLayerNetwork.java:1430)
at org.deeplearning4j.nn.multilayer.MultiLayerNetwork.fit(MultiLayerNetwork.java:1482)
at org.deeplearning4j.nn.multilayer.MultiLayerNetwork.fit(MultiLayerNetwork.java:1529)
at projecta_learning.TrainingLFW.main(TrainingLFW.java:64)

TrainingLFW.txt

[plankes-projects]

The problem is following:

In the config, the last layer defines .nOut(NUM_OF_CLASSES)
This has to match the number of subdirectories you have.

[lock]

This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.