You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@ignite.apache.org by "Maxim Muzafarov (Jira)" <ji...@apache.org> on 2019/10/01 15:11:00 UTC

[jira] [Updated] (IGNITE-10849) [ML] Prepare a benchmark to compare Ignite ML and Spark MLeap inference performance

     [ https://issues.apache.org/jira/browse/IGNITE-10849?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Maxim Muzafarov updated IGNITE-10849:
-------------------------------------
    Labels: await  (was: )

> [ML] Prepare a benchmark to compare Ignite ML and Spark MLeap inference performance
> -----------------------------------------------------------------------------------
>
>                 Key: IGNITE-10849
>                 URL: https://issues.apache.org/jira/browse/IGNITE-10849
>             Project: Ignite
>          Issue Type: Improvement
>          Components: ml
>    Affects Versions: 2.8
>            Reporter: Anton Dmitriev
>            Priority: Minor
>              Labels: await
>             Fix For: 2.8
>
>
> In IGNITE-10810 we have added functionality that allows to import Spark models saved using MLeap. Some of these models we already have in Ignite ML. The goal of this task is to compare inference performance of Ignite ML and Spark MLeap models in our environment.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)