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 2017/12/29 11:56:36 UTC

[GitHub] gzygzy9211 opened a new issue #9225: Caffe_Converter produce mx.symbol.SoftmaxOuput rather than SoftmaxActivation

gzygzy9211 opened a new issue #9225: Caffe_Converter produce mx.symbol.SoftmaxOuput rather than SoftmaxActivation
URL: https://github.com/apache/incubator-mxnet/issues/9225
 
 
   incubator-mxnet/tools/caffe_converter/convert_symbol.py 
   According to the py code, it produce  mx.symbol.SoftmaxOuput  for caffe's  layer of type "Softmax"
   
   However mx.symbol.SoftmaxOuput needs label and it computes gradient w.r.t to its input, which is not expected during inference.
   
   So am I right that we should use mx.symbol.SoftmaxActivation while converting caffe's "Softmax" layer?
   

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