singa-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "ASF subversion and git services (JIRA)" <>
Subject [jira] [Commented] (SINGA-383) Add Separable Convolution for autograd
Date Fri, 24 Aug 2018 02:59:00 GMT


ASF subversion and git services commented on SINGA-383:

Commit ca70bdf3f02412f216d10e8d4ba6c265bdd139ee in incubator-singa's branch refs/heads/master
from xuewanqi
[;h=ca70bdf ]

SINGA-383 Add Separable Convolution for autograd

- let Conv2d layer support 'groups' paramters, for grouped convolution.

- implement Separable Convolution layer.

- add unit test case for new developed SeparableConv2d layer.

- the implemented SeparableConv2d layer has passed both unit test and network test.

> Add Separable Convolution for autograd
> --------------------------------------
>                 Key: SINGA-383
>                 URL:
>             Project: Singa
>          Issue Type: New Feature
>            Reporter: wangwei
>            Priority: Major
> This type of convolution is used in [Xception model|]
and is supported by [other libraries|[].]
> To implement it in Singa, we create a new operation (separable_conv_2d) by calling a
depthwise_conv_2d (normal convolution with number of output channels=1, and number of groups
= number of input channels); and then calling normal convolution with number of groups=1,
and kernel size=1, i.e. pointwise convolution.

This message was sent by Atlassian JIRA

View raw message