I’m looking for tips on how to create a Sequence to sequence DataBunch that will fit into the existing functionality of the fastai library well. My goal is something that works with TextDataBunch
, but if there was a way to abstract out the NLP bits that would be even better. What I’ve tried:
-
Subclass of TextDataBunch
I can make this work with a customcreate(..)
method, but many of the convenient loaders (from_*) are expecting either class or LM labels. -
Custom ItemList
In theory aSeqTextList: TextList
and something likeTextSequence: Text
should be similar to the example covered in the custom item list tutorial, but I haven’t found a way to get the processors to work well with the target sequence. -
Use a basic
Seq2Seq: Dataset
This was demonstrated in L11, but there are many caveats with this approach in fast.ai_v1.
Any and all ideas are appreciated!