[GitHub] anirudhacharya commented on issue #7490: How to train with input layer dropout?

[GitBox <gi...@apache.org>]

anirudhacharya commented on issue #7490: How to train with input layer dropout?
URL: https://github.com/apache/incubator-mxnet/issues/7490#issuecomment-410885169
 
 
   @thomasmooon In your Example_1, please replace
   ```R
   data.withDroput <- mx.nd.Dropout(data = data, p = 0.5)
   ```
   with
   ```R
   data.withDroput <- mx.nd.Dropout(data = data, p = 0.5, mode='always')
   ```
   After providing the ``mode`` attribute, I get the following results -
   ```R
   data
          [,1] [,2]
   [1,]    3    9
   [2,]    4    9
   [3,]    6    6
   [4,]    9    6
   [5,]    2    1
   
   data.withDroput
          [,1] [,2]
   [1,]    0    0
   [2,]    0    0
   [3,]    0    0
   [4,]    0   12
   [5,]    0    0
   ```
   
   If this has addressed your problem, please close this issue.

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