[
https://issues.apache.org/jira/browse/SINGA-147?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15192116#comment-15192116
]
wangwei commented on SINGA-147:
-------------------------------
pls refer to this page for the status of SINGA,
http://singa.apache.org/develop/schedule.html.
we have implemented some example applications for image recognition and NLP,
http://singa.apache.org/docs/examples.html.
this project aims to develop a mobile app which uses the model trained by
SINGA.
we prefer to image/video recognition applications.
> Run SINGA applications on mobile devices
> ----------------------------------------
>
> Key: SINGA-147
> URL: https://issues.apache.org/jira/browse/SINGA-147
> Project: Singa
> Issue Type: New Feature
> Reporter: wangwei
> Labels: gsoc, gsoc2016, mentor
>
> Mobile devices (e.g., mobile phones) are good platforms for running deep
> learning applications, e.g., object or speech recognition, since they can
> record video and audio, and take pictures.
> A simple implementation for such applications would send the content (e.g.,
> video or images) back to central servers, which requires internet connection
> and consumes mobile data. Considering that the recognition task is cheap
> (cheaper than training tasks), we can implement mobile apps to do the
> recognition tasks on the mobile devices. In this way, we can run the
> applications off-line, which is very convenient for users.
> This JIRA issue is going to re-implement some SINGA functions on mobile app
> development platforms to create a mobile app (android/ios) for object/speech
> recognition.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)