jwfromm commented on code in PR #11446:
URL: https://github.com/apache/tvm/pull/11446#discussion_r882025015
##########
python/tvm/relay/frontend/onnx.py:
##########
@@ -4978,10 +4978,30 @@ def _impl_v1(cls, inputs, attr, params):
return _expr.TupleWrapper(_expr.Tuple(result), len(result))
+class Round(OnnxOpConverter):
+ """Operator converter for round op."""
+
+ @classmethod
+ def _impl_v11(cls, inputs, attr, params):
+ # See the tutorial for full implementation details:
+ #
https://www.youtube.com/watch?v=fZvNG-oKK5Q&list=PL_4zDggB-DBpynCEnC9hV-1euZrP3xDRK&index=4
Review Comment:
It would be better to explain what onnx is doing (and why we need to handle
it specially) in the comment rather than linking to youtube.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
