[GitHub] edmBernard commented on issue #7522: how to calculate an evaluation metric using intermediate layer output?

[gi...@git.apache.org]

edmBernard commented on issue #7522: how to calculate an evaluation metric using intermediate layer output?
URL: https://github.com/apache/incubator-mxnet/issues/7522#issuecomment-323512819
 
 
   you can define this layer in output : 
   ```python
   def get_symbol():
       data = mx.symbol.Variable(name="data")
       inter = mx.symbol.FullyConnected(data=data, num_hidden=4096, name="inter")
       fc1 = mx.symbol.FullyConnected(data=inter, num_hidden=4096, name="fc1")
       softmax = mx.symbol.SoftmaxOutput(data=fc1, name='softmax')
   return mx.symbol.Group([softmax, inter])
   ```
   look at [this](https://github.com/apache/incubator-mxnet/blob/master/example/python-howto/multiple_outputs.py)
 
----------------------------------------------------------------
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