[GitHub] spark issue #18313: [SPARK-21087] [ML] CrossValidator, TrainValidationSplit ...

[hhbyyh <gi...@git.apache.org>]

Github user hhbyyh commented on the issue:

    https://github.com/apache/spark/pull/18313
  
    Current implementation of `CrossValidator` (with or without this PR) **NEVER** holds all the trained models in the driver memory at the same time. It collects models sequentially and allows GC to clear previous trained models.  
    
    With all due respect, for the record, I strongly vote against keeping all the models in the CrossValidatorModel in any way, which makes it impractical for any production usage.



---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org