2015-05-19 08:11:33 -0600 | commented answer | Neuronal network predict access violation @mshabunin. Maybe that was the reason for it. I don't have the time to check it myself. Thanks anyway! |
2015-05-12 03:53:30 -0600 | commented question | Neuronal network predict access violation About 15. But that should be enough to give me at least a not very precise network. |
2015-05-12 03:50:26 -0600 | answered a question | Neuronal network predict access violation I switched to the FANN library. Couldn't find the reason for the Crash. |
2015-05-06 13:07:31 -0600 | asked a question | Neuronal network predict access violation Hello, I'v been trying to use the ANN_MLP class for learning and predicting objects regarding their shape. But I'm getting an Access Violation as soon as i try to predict a test sample. I have an input vector with train samples that looks like that for 2 different classes:
My corresponding classes vector looks like this:
I think there is something going wrong while learning. Because the weights in the .XML of the saved neuronal Network seem almost identical and extremely small when I compare them to the results of a .XML I found online. Extract from my .XML:
For me this seems kind of odd. Since the values are just rediculous small.
However here the part of the code where I do the setup and training: I make the prediction with an row of values, for example:
Both the classification and train matrices have the type CV_32F (float). I tried different settings and layer sizes - even if I should get at least a moderate result with any settings (these ones are just the last I tried). I already normalized the values in the train matrix ( I think the algorithm does this by itself ) with no success. Maybe you guys have a clue about it. Thank you so much. |