sxjscience commented on a change in pull request #16170: Update KL Divergence
formula
URL: https://github.com/apache/incubator-mxnet/pull/16170#discussion_r325907887
##########
File path: python/mxnet/gluon/loss.py
##########
@@ -408,7 +408,7 @@ class KLDivLoss(Loss):
.. math::
- L = \sum_i {label}_i * \big[\log({label}_i) - {pred}_i\big]
+ L = \sum_i {label}_i * \big[\log({label}_i) - \log({pred}_i)\big]
Review comment:
It looks correct at first glance. However, I've checked the implementation
again and it looks that the previous version is correct.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to 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
