[GitHub] [incubator-mxnet] wkcn commented on a change in pull request #13612: add pos_weight for SigmoidBinaryCrossEntropyLoss

[GitBox <gi...@apache.org>]

wkcn commented on a change in pull request #13612: add pos_weight for SigmoidBinaryCrossEntropyLoss
URL: https://github.com/apache/incubator-mxnet/pull/13612#discussion_r262814285
 
 

 ##########
 File path: python/mxnet/gluon/loss.py
 ##########
 @@ -227,13 +234,14 @@ def __init__(self, from_sigmoid=False, weight=None, batch_axis=0, **kwargs):
         super(SigmoidBinaryCrossEntropyLoss, self).__init__(weight, batch_axis, **kwargs)
         self._from_sigmoid = from_sigmoid
 
-    def hybrid_forward(self, F, pred, label, sample_weight=None):
+    def hybrid_forward(self, F, pred, label, pos_weight=1, sample_weight=None):
         label = _reshape_like(F, label, pred)
         if not self._from_sigmoid:
             # We use the stable formula: max(x, 0) - x * z + log(1 + exp(-abs(x)))
-            loss = F.relu(pred) - pred * label + F.Activation(-F.abs(pred), act_type='softrelu')
+            log_weight = 1 + (pos_weight - 1) * label
+            loss = pred - pred*label + log_weight*(F.Activation(-F.abs(pred), act_type='softrelu') + F.relu(-pred))
         else:
-            loss = -(F.log(pred+1e-12)*label + F.log(1.-pred+1e-12)*(1.-label))
+            loss = -(F.log(pred+1e-12)*label*pos_weight + F.log(1.-pred+1e-12)*(1.-label))
 
 Review comment:
   Please add a branch if pos_weight == 1: else statement to keep the performance. Thanks!

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services