[
https://issues.apache.org/jira/browse/SINGA-363?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
wentong resolved SINGA-363.
---------------------------
Resolution: Done
> 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)
