FlatNetwork trained values don't get stored in the xml file
Closed this issue · 2 comments
GoogleCodeExporter commented
What steps will reproduce the problem?
1. Train a BasicNetwork like in the MarketTrain example using the new
FlatNetwork mechanism
2. flatNetwork's weights[] array update correctly during training but at the
end it should unflatten learned values to parent BasicNetwork. This doesn't
happen in latest code.
3.
What is the expected output? What do you see instead?
I see the original random weights and thresholds in the trained xml file
instead of learned ones.
Please use labels and text to provide additional information.
Original issue reported on code.google.com by dmi...@gmail.com
on 16 Sep 2010 at 4:23
GoogleCodeExporter commented
i was able to get it to work by adding:
network.getStructure().updateFlatNetwork();
at the end of the
trainConsole(final Train train, final BasicNetwork network, final NeuralDataSe,
trainingSet, final int minutes)
method
EncogUtility.java at line 229. Not sure if this is the right thing to do though
Original comment by dmi...@gmail.com
on 16 Sep 2010 at 4:49
GoogleCodeExporter commented
Original comment by dmi...@gmail.com
on 18 Sep 2010 at 8:02
- Changed state: Fixed