0

I saw how to do this from a DataSet object, and I saw a setLabel method, and I saw a getLabelMaskArrays, but none of these are what I'm looking for.

Am I just blind or is there not a way?

Thanks

Arthur Dunbar
  • 23
  • 5

1 Answers1

0

Masking is for variable length time series in RNNs. Most of the time you don't need it. Our built in sequence dataset iterators also tend to handle these cases. For more details see our rnn page: https://deeplearning4j.org/usingrnns

Adam Gibson
  • 3,055
  • 1
  • 10
  • 12
  • Is it possible to get a list of the classes a ComputationGraph object is able to distinguish between? I have one trained on a dataset that has several types of article, economic, commodity, and currency (and others) could I get that list from the ComputationGraph object trained on them? (if it makes a difference it is a Convolutional Network) – Arthur Dunbar Jul 18 '18 at 01:24
  • It's domain specific. A computation graph is *just* matrix math. It's on you to track it. – Adam Gibson Jul 18 '18 at 07:54
  • Thank you. I'll come up with some other way of preserving it then. – Arthur Dunbar Jul 23 '18 at 21:03