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

Posted to dev@singa.apache.org by "ASF subversion and git services (JIRA)" <ji...@apache.org> on 2018/05/19 04:26:00 UTC

[jira] [Commented] (SINGA-363) Add DenseNet for ImageNet classification

    [ https://issues.apache.org/jira/browse/SINGA-363?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16481454#comment-16481454 ] 

ASF subversion and git services commented on SINGA-363:
-------------------------------------------------------

Commit 8a1d98a39385137b6250bc36c5a558c9d731aa45 in incubator-singa's branch refs/heads/master from [~asyz13jinage]
[ https://git-wip-us.apache.org/repos/asf?p=incubator-singa.git;h=8a1d98a ]

SINGA-363 Add DenseNet for Imagenet classification


> Add DenseNet for ImageNet classification
> ----------------------------------------
>
>                 Key: SINGA-363
>                 URL: https://issues.apache.org/jira/browse/SINGA-363
>             Project: Singa
>          Issue Type: New Feature
>            Reporter: wentong
>            Priority: Minor
>
> The DenseNet[ |http://arxiv.org/abs/1602.07261]models are a series of deep CNN models with high performance.
>  We convert the parameters pre-trained from Pytorch into pickle dictionary and load them into the net created using SINGA FeedForwardNet.
> Coding style and format will follow previous examples.
> In the meantime, some other minor bugs in "examples" folder would be fixed in order to run in Python 3 environment.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)