singa-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "wangwei (JIRA)" <>
Subject [jira] [Created] (SINGA-383) Add Separable Convolution for autograd
Date Fri, 13 Jul 2018 06:54:00 GMT
wangwei created SINGA-383:

             Summary: Add Separable Convolution for autograd
                 Key: SINGA-383
             Project: Singa
          Issue Type: New Feature
            Reporter: wangwei

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