[
https://issues.apache.org/jira/browse/SINGA-278?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15771780#comment-15771780
]
ASF subversion and git services commented on SINGA-278:
-------------------------------------------------------
Commit aae9d3e6bd838de7843bbd09cc214724e1c05e7a in incubator-singa's branch
refs/heads/master from [~Xiangrui]
[ https://git-wip-us.apache.org/repos/asf?p=incubator-singa.git;h=aae9d3e ]
SINGA-278 Convert trained caffe parameters to singa
Convert trained caffe parameters to singa
use pillow to load images
put models and some dependent files in dropbox
execute run.sh to run vgg model
> Convert trained caffe parameters to singa
> -----------------------------------------
>
> Key: SINGA-278
> URL: https://issues.apache.org/jira/browse/SINGA-278
> Project: Singa
> Issue Type: New Feature
> Reporter: Xiangrui
>
> Convert trained parameters of caffe model to singa.
> Run vgg as an example. Some tricks should be noticed:
> 1. The order of image axes in caffe is height, width and channels due to
> opencv implementation, while it is width, height, channels in singa if you
> use python PIL.
> 2. Another problem caused by these two libraries is the order of channels,
> BGR(caffe, opencv) v.s. RGB(singa, PIL).
> 3. It needs to transpose the weight tensor in InnerProduct(Dense) layer.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
