You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@beam.apache.org by "Andy Ye (Jira)" <ji...@apache.org> on 2022/04/25 15:40:00 UTC

[jira] [Created] (BEAM-14362) Add flag to drop example from PredicitonResult

Andy Ye created BEAM-14362:
------------------------------

             Summary: Add flag to drop example from PredicitonResult
                 Key: BEAM-14362
                 URL: https://issues.apache.org/jira/browse/BEAM-14362
             Project: Beam
          Issue Type: Sub-task
          Components: sdk-py-core
            Reporter: Andy Ye


RunInference currently returns both the example/input and prediction. 

```

PredictionResult:

  example: torch(...)

  inference: torch(...)

```

Users may want the ability to only return the inference to minimize potential memory/serialization issues later in the pipeline. They can do this with a flag, and the return value may look like

```

PredictionResult:

  example: None

  inference: torch(...)

```



--
This message was sent by Atlassian Jira
(v8.20.7#820007)