提交 59e3cce7 authored 作者: Vincent Dumoulin's avatar Vincent Dumoulin

Add 'atrous convolutions' reference

上级 57508672
...@@ -885,11 +885,12 @@ Dilated convolutions ...@@ -885,11 +885,12 @@ Dilated convolutions
-------------------- --------------------
Those familiar with the deep learning literature may have noticed the term Those familiar with the deep learning literature may have noticed the term
"dilated convolutions" (or *convolutions à trous*) appear in recent papers. Here "dilated convolutions" (or "atrous convolutions", from the French expression
we attempt to provide an intuitive understanding of dilated convolutions. For a *convolutions à trous*) appear in recent papers. Here we attempt to provide an
more in-depth description and to understand in what contexts they are applied, intuitive understanding of dilated convolutions. For a more in-depth description
see `Chen et al. (2014) <https://arxiv.org/abs/1412.7062>`_ [#]_; `Yu and Koltun and to understand in what contexts they are applied, see `Chen et al. (2014)
(2015) <https://arxiv.org/abs/1511.07122>`_ [#]_. <https://arxiv.org/abs/1412.7062>`_ [#]_; `Yu and Koltun (2015)
<https://arxiv.org/abs/1511.07122>`_ [#]_.
Dilated convolutions "inflate" the kernel by inserting spaces between the kernel Dilated convolutions "inflate" the kernel by inserting spaces between the kernel
elements. The dilation "rate" is controlled by an additional hyperparameter elements. The dilation "rate" is controlled by an additional hyperparameter
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论