gaurav-gireesh commented on a change in pull request #12750: [MXNET -1030]
Cosine Embedding Loss
URL: https://github.com/apache/incubator-mxnet/pull/12750#discussion_r228357724
##########
File path: tests/python/unittest/test_loss.py
##########
@@ -348,6 +348,22 @@ def test_triplet_loss():
optimizer='adam')
assert mod.score(data_iter, eval_metric=mx.metric.Loss())[0][1] < 0.05
+@with_seed()
Review comment:
> Please add additional tests for label = -1 and hybridization.
1. Added tests for label 1 and -1 in a randomly generated set of labels,
2. This function is meant to be utility similar to cosine_distance.
----------------------------------------------------------------
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
