evahlis opened a new issue #7918: How to use the sample_weight parameter of 
SoftmaxCrossEntropyLoss?
URL: https://github.com/apache/incubator-mxnet/issues/7918
 
 
   Hi,
   The documentation of the loss function 
([here](https://mxnet.incubator.apache.org/api/python/gluon.html?highlight=softmaxcr#mxnet.gluon.loss.SoftmaxCrossEntropyLoss))
 says that there is a parameter called sample_weight, presumably allowing 
reweighing of the loss for each sample in each batch. 
   
   How to use it? I have an imbalanced training data and want to multiply the 
loss by the inverse of the class frequency.
   
   Thanks!

----------------------------------------------------------------
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:
[email protected]


With regards,
Apache Git Services

Reply via email to