roywei commented on a change in pull request #12750: [MXNET -1030] Cosine
Embedding Loss
URL: https://github.com/apache/incubator-mxnet/pull/12750#discussion_r223785717
##########
File path: python/mxnet/gluon/loss.py
##########
@@ -706,3 +706,53 @@ def hybrid_forward(self, F, pred, positive, negative):
axis=self._batch_axis, exclude=True)
loss = F.relu(loss + self._margin)
return _apply_weighting(F, loss, self._weight, None)
+
+class CosineEmbeddingLoss(Loss):
+ r"""For a target label 1 or -1, vectors target and pred, the function
computes the cosine distance
+ between the vectors. This can be interpretted as how similar/dissimilar
two input vectors are.
+
+
+ `pred`, `target` can have arbitrary shape as long as they have the same
number of elements.
Review comment:
Please refer to[ huber loss
](https://github.com/gaurav-gireesh/incubator-mxnet/blob/cosineloss/python/mxnet/gluon/loss.py#L478)and
use only `{case}`, remove `{gather}`. maybe your mathjax version and what we
used in the website is different, so some formula is not recognized. A safe way
is to use only what have been correctly rendered, those should be more than
enough
----------------------------------------------------------------
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
