Skip to content
项目
群组
代码片段
帮助
当前项目
正在载入...
登录 / 注册
切换导航面板
P
pytensor
项目
项目
详情
活动
周期分析
仓库
仓库
文件
提交
分支
标签
贡献者
图表
比较
统计图
议题
0
议题
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
CI / CD
CI / CD
流水线
作业
日程
统计图
Wiki
Wiki
代码片段
代码片段
成员
成员
折叠边栏
关闭边栏
活动
图像
聊天
创建新问题
作业
提交
问题看板
Open sidebar
testgroup
pytensor
Commits
ad16a12c
提交
ad16a12c
authored
10月 15, 2015
作者:
Pascal Lamblin
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Fix PDF generation on the site
上级
662ea98e
隐藏空白字符变更
内嵌
并排
正在显示
2 个修改的文件
包含
20 行增加
和
18 行删除
+20
-18
docgen.py
doc/scripts/docgen.py
+1
-1
neighbours.py
theano/tensor/nnet/neighbours.py
+19
-17
没有找到文件。
doc/scripts/docgen.py
浏览文件 @
ad16a12c
...
...
@@ -131,7 +131,7 @@ if __name__ == '__main__':
inopt
=
[
docpath
,
workdir
]
if
files
is
not
None
:
inopt
.
extend
(
files
)
sphinx
.
main
([
''
,
'-b'
,
builder
]
+
extraopts
+
inopt
)
sphinx
.
build_
main
([
''
,
'-b'
,
builder
]
+
extraopts
+
inopt
)
if
options
[
'--all'
]
or
options
[
'--rst'
]:
mkdir
(
"doc"
)
...
...
theano/tensor/nnet/neighbours.py
浏览文件 @
ad16a12c
...
...
@@ -67,18 +67,20 @@ class Images2Neibs(Op):
Returns
-------
matrix
A 2D matrix, written using the following pattern
idx = 0
for i in xrange(list 1 dim)
for j in xrange(list 2 dim)
for k in <image column coordinates>
for l in <image row coordinates>
output[idx,:]
= flattened version of ten4[i,j,l:l+r,k:k+c]
idx += 1
A 2D matrix, written using the following pattern::
idx = 0
for i in xrange(list 1 dim)
for j in xrange(list 2 dim)
for k in <image column coordinates>
for l in <image row coordinates>
output[idx,:]
= flattened version of ten4[i,j,l:l+r,k:k+c]
idx += 1
.. note:: The op isn't necessarily implemented internally with these
for loops, they're just the easiest way to describe the output
pattern.
for loops, they're just the easiest way to describe the output
pattern.
"""
ten4
=
T
.
as_tensor_variable
(
ten4
)
...
...
@@ -456,15 +458,15 @@ def images2neibs(ten4, neib_shape, neib_step=None, mode='valid'):
.. note:: Currently the step size should be chosen in the way that the
corresponding dimension :math:`i` (width or height) is equal to
:math:`n * step
\
_size_i + neib
\
_shape_i` for some :math:`n`
mode : {'valid', 'ignore_borders', 'wrap_centered}
mode : {'valid', 'ignore_borders', 'wrap_centered
'
}
``valid``
Requires an input that is a multiple of the
pooling factor (in each direction).
Requires an input that is a multiple of the
pooling factor (in each direction).
``ignore_borders``
Same as valid, but will ignore the borders if the shape(s) of
the input is not a multiple of the pooling factor(s).
Same as valid, but will ignore the borders if the shape(s) of
the input is not a multiple of the pooling factor(s).
``wrap_centered``
?? TODO comment
?? TODO comment
Returns
-------
...
...
编写
预览
Markdown
格式
0%
重试
或
添加新文件
添加附件
取消
您添加了
0
人
到此讨论。请谨慎行事。
请先完成此评论的编辑!
取消
请
注册
或者
登录
后发表评论