[GitHub] jeremiedb commented on issue #7524: Is there a tutorial of using mxnet R LSTM for time series forecasting?

[gi...@git.apache.org]

jeremiedb commented on issue #7524: Is there a tutorial of using mxnet R LSTM for time series forecasting? 
URL: https://github.com/apache/incubator-mxnet/issues/7524#issuecomment-323533891
 
 
   There's a pull request #7470 meant to facilitate training of various flavours of RNN and support iterators feeding various sequence lengths. 
   
   Current design is more adapted to text as it assumes that data feed is of dimension : seq.length X batch.size, to which embedding is applied. If you take a look at the demo of the new functionalities [here](https://github.com/jeremiedb/mxnet_R_bucketing), you can see that it would be quite simple to adapt the model graph by omitting the embedding operator and instead have an iterator that feed data of shape features.number X batch.size X sequence.length. 
   
   By working with the mx.symbol.RNN operator, the modeling approach is essentially the same as for the feedforwardmode: just need to build the symbol graph, for which the `rnn.graph` is a helper function and then train using `mx.rnn.buckets`. Caveat: for now only GPU is supported. 
   
   Your feedback on whether you think these functionalities would be helpful are most welcome. 
 
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services