You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@submarine.apache.org by "Zhankun Tang (Jira)" <ji...@apache.org> on 2019/12/17 03:39:00 UTC
[jira] [Resolved] (SUBMARINE-27) [Submarine] Support for executing
tensorflow algorithm files on hdfs
[ https://issues.apache.org/jira/browse/SUBMARINE-27?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Zhankun Tang resolved SUBMARINE-27.
-----------------------------------
Resolution: Duplicate
> [Submarine] Support for executing tensorflow algorithm files on hdfs
> --------------------------------------------------------------------
>
> Key: SUBMARINE-27
> URL: https://issues.apache.org/jira/browse/SUBMARINE-27
> Project: Apache Submarine
> Issue Type: New Feature
> Reporter: Xun Liu
> Assignee: Xun Liu
> Priority: Major
>
> Now the submarine project can only execute the algorithm files in the docker image.
> Need support for executing tensorflow algorithm files on HDFS.
> 1. The user uploads the algorithm file to the HDFS directory manually or via zeppelin.
> 2. In the base image provided by submarine, Increase the path parameters according to the specified algorithm, Download the algorithm file from HDFS to the `/tmp/` directory.
> {code:java}
> hadoop-yarn-project/hadoop-yarn/hadoop-yarn-applications/hadoop-yarn-submarine/src/main/docker/base/ubuntu-16.04/Dockerfile.cpu.tf_1.8.0
> and
> hadoop-yarn-project/hadoop -yarn/hadoop-yarn-applications/hadoop-yarn-submarine/src/main/docker/base/ubuntu-16.04/Dockerfile.gpu.tf_1.8.0{code}
> 3. Add parameters to the algorithm file path in submarine project.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@submarine.apache.org
For additional commands, e-mail: dev-help@submarine.apache.org