[
https://issues.apache.org/jira/browse/SINGA-300?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15871249#comment-15871249
]
ASF subversion and git services commented on SINGA-300:
-------------------------------------------------------
Commit c0317d185004ea594f19b74cbb9bc2c97e66a7b1 in incubator-singa's branch
refs/heads/master from [~wangwei.cs]
[ https://git-wip-us.apache.org/repos/asf?p=incubator-singa.git;h=c0317d1 ]
SINGA-300 - Add residual networks for imagenet classification
Add the wide residual network for imagenet serving; refer to
https://github.com/szagoruyko/wide-residual-networks
convert original resnet from torch to singa. tested wide resnet;
> Add residual networks for imagenet classification
> -------------------------------------------------
>
> Key: SINGA-300
> URL: https://issues.apache.org/jira/browse/SINGA-300
> Project: Singa
> Issue Type: New Feature
> Reporter: wangwei
>
> This ticket would add a couple of residual networks trained over ImageNet.
> Pre-trained parameters from torch are converted into python dictionary and
> dumped via cPickle.
> In particular, the following residual networks are implemented
> 1. Original residual network https://arxiv.org/abs/1512.03385
> 2. Pre-activation residual network https://arxiv.org/abs/1603.05027
> 3. Wide residual network http://arxiv.org/abs/1605.07146
> reference:
> https://github.com/facebook/fb.resnet.torch
> https://github.com/szagoruyko/wide-residual-networks
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
