ryanthompson591 commented on code in PR #21806:
URL: https://github.com/apache/beam/pull/21806#discussion_r897088019
##########
sdks/python/apache_beam/ml/inference/base.py:
##########
@@ -125,11 +130,14 @@ def load_model(self) -> ModelT:
return self._unkeyed.load_model()
def run_inference(
- self, batch: Sequence[Tuple[KeyT, ExampleT]], model: ModelT,
- **kwargs) -> Iterable[Tuple[KeyT, PredictionT]]:
+ self,
+ batch: Sequence[Tuple[KeyT, ExampleT]],
+ model: ModelT,
+ extra_kwargs: Optional[Dict[str, Any]] = None
+ ) -> Iterable[Tuple[KeyT, PredictionT]]:
keys, unkeyed_batch = zip(*batch)
return zip(
- keys, self._unkeyed.run_inference(unkeyed_batch, model, **kwargs))
+ keys, self._unkeyed.run_inference(unkeyed_batch, model, extra_kwargs))
Review Comment:
I'm worried about growing the interface in a lot of places to handle
arguments that are only applicable to a single framework.
If an argument is shouldn't be in a framework ideally it should fail and
give an error.
--
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]
