You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2019/02/20 20:02:15 UTC

[GitHub] drivanov commented on issue #14208: Add support for fast variable-length LSTM

drivanov commented on issue #14208: Add support for fast variable-length LSTM
URL: https://github.com/apache/incubator-mxnet/pull/14208#issuecomment-465732588
 
 
   @stephenrawls: With following simple changes in your `test_varlength_lstm.py`:
   ```
   ctx = mx.gpu()
   X = mx.nd.random.randn(timesteps, batch_size, nchannels).as_in_context(ctx)
   valid_lengths = mx.nd.array([10,10,10,7,6]).as_in_context(ctx) # [10,10,10,10,6] seems to work fine
   ```
   you don't need to modify `imperative_utils.h`

----------------------------------------------------------------
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