[
https://issues.apache.org/jira/browse/SINGA-397?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16663254#comment-16663254
]
Ngin Yun Chuan commented on SINGA-397:
--------------------------------------
Hi Junyou,
For the issue regarding making of predictions, that `curl` command is intended
to run on the Unix shell rather than the Python CLI. In other words, to make
predictions, you make a POST request to `predictor_host` (e.g.
12.0.0.1:3000/predict) of an inference job - you can do that on Python with the
`requests` module (check the code in `client-usage.py`).
For the 2nd point on using the dataset on your local system when Rafiki is
deployed on your local system as well - our team will be discussing this and
giving you a follow up.
> Deployment Issues for Rafiki
> ----------------------------
>
> Key: SINGA-397
> URL: https://issues.apache.org/jira/browse/SINGA-397
> Project: Singa
> Issue Type: Test
> Environment: ubuntu 18, local machine
> Reporter: Junyou Chen
> Priority: Major
> Attachments: 1.png, 2.png, 2018-10-24 13-03-56 的屏幕截图.png
>
>
> After I deployed Rafiki on my own machine by following the Quick Setup
> section in the Developer Guide, I tried to run the $client-usage.py$ but
> failed(as picture 1 shows. system halted with no feedback). Also, I followed
> several examples in the User Guide, but there are still some problems(shown
> in picture 2).
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
