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 2017/11/27 11:48:39 UTC

[GitHub] AlexBinder commented on issue #8556: [Call for Contribution] Image augmenter operators

AlexBinder commented on issue #8556: [Call for Contribution] Image augmenter operators
URL: https://github.com/apache/incubator-mxnet/issues/8556#issuecomment-347159214
 
 
   I like the idea how it is done in pytorch - composing a sequence of transforms.
   
   also: random_crop is a useful idea not mentioned here.
   same: a random rotation by 90degrees ... if you are in problems with imaging of small sample size rotation symmetric data.
   
   one point to check is: that iterators should be able to work with variable size input images if a resize or crop operator is used ... bcs the output will then have fixed size again, so it would fit into an ndarray. 

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