You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by gi...@git.apache.org on 2017/08/25 01:14:58 UTC

[GitHub] thvasilo commented on issue #612: "Slice end index out of range" on eval data

thvasilo commented on issue #612: "Slice end index out of range" on eval data
URL: https://github.com/apache/incubator-mxnet/issues/612#issuecomment-324798076
 
 
   For me the case was that I had trained the model using one batch size and then tried to evaluate using a different one.
   
   E.g.
   
   ```python
   train_iter = mx.io.NDArrayIter(X_train, y_train, batch_size, shuffle=True)
   test_iter = mx.io.NDArrayIter(X_test, y_test, batch_size)
   ```
   
   Note how I assign the same batch size to both iterators. When I tried using different batch sizes it would error out. Not sure if this is a bug or not, I don't see why the batch size needs to be tied to the model after training.
 
----------------------------------------------------------------
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