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
54a1c069
提交
54a1c069
authored
6月 23, 2016
作者:
Cesar Laurent
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Corrected c_code.
上级
c5d46d06
隐藏空白字符变更
内嵌
并排
正在显示
1 个修改的文件
包含
79 行增加
和
65 行删除
+79
-65
pool.py
theano/tensor/signal/pool.py
+79
-65
没有找到文件。
theano/tensor/signal/pool.py
浏览文件 @
54a1c069
...
@@ -9,7 +9,6 @@ from __future__ import absolute_import, print_function, division
...
@@ -9,7 +9,6 @@ from __future__ import absolute_import, print_function, division
import
warnings
import
warnings
import
numpy
import
numpy
from
six
import
integer_types
from
six.moves
import
xrange
from
six.moves
import
xrange
import
six.moves.builtins
as
builtins
import
six.moves.builtins
as
builtins
import
theano
import
theano
...
@@ -397,14 +396,19 @@ class Pool(OpenMPOp):
...
@@ -397,14 +396,19 @@ class Pool(OpenMPOp):
z
,
=
out
z
,
=
out
fail
=
sub
[
'fail'
]
fail
=
sub
[
'fail'
]
ignore_border
=
int
(
self
.
ignore_border
)
ignore_border
=
int
(
self
.
ignore_border
)
ws0
,
ws1
=
ws
st0
,
st1
=
stride
pd0
,
pd1
=
pad
if
self
.
openmp
:
if
self
.
openmp
:
omp_parallel
=
'#pragma omp parallel for private(r_st, r_end, c_st, c_end, collector) schedule(static)'
omp_parallel
=
'#pragma omp parallel for private(r_st, r_end, c_st, c_end, collector) schedule(static)'
else
:
else
:
omp_parallel
=
''
omp_parallel
=
''
ccode
=
"""
ccode
=
"""
// Getting ws, stride and pad
int ws0, ws1, st0, st1, pd0, pd1;
ws0 = *((npy_intp*)PyArray_GETPTR1(
%(ws)
s, 0));
ws1 = *((npy_intp*)PyArray_GETPTR1(
%(ws)
s, 1));
st0 = *((npy_intp*)PyArray_GETPTR1(
%(stride)
s, 0));
st1 = *((npy_intp*)PyArray_GETPTR1(
%(stride)
s, 1));
pd0 = *((npy_intp*)PyArray_GETPTR1(
%(pad)
s, 0));
pd1 = *((npy_intp*)PyArray_GETPTR1(
%(pad)
s, 1));
int typenum = PyArray_ObjectType((PyObject*)
%(x)
s, 0);
int typenum = PyArray_ObjectType((PyObject*)
%(x)
s, 0);
int z_r, z_c; // shape of the output
int z_r, z_c; // shape of the output
int r, c; // shape of the padded_input
int r, c; // shape of the padded_input
...
@@ -415,9 +419,9 @@ class Pool(OpenMPOp):
...
@@ -415,9 +419,9 @@ class Pool(OpenMPOp):
}
}
r = PyArray_DIMS(
%(x)
s)[2];
r = PyArray_DIMS(
%(x)
s)[2];
c = PyArray_DIMS(
%(x)
s)[3];
c = PyArray_DIMS(
%(x)
s)[3];
r +=
%(pd0)
s
* 2;
r +=
pd0
* 2;
c +=
%(pd1)
s
* 2;
c +=
pd1
* 2;
if (
%(pd0)
s != 0 &&
%(pd1)
s
!= 0 && !
%(ignore_border)
s)
if (
pd0 != 0 && pd1
!= 0 && !
%(ignore_border)
s)
{
{
PyErr_SetString(PyExc_ValueError,
PyErr_SetString(PyExc_ValueError,
"padding must be (0,0) when ignore border is False");
"padding must be (0,0) when ignore border is False");
...
@@ -426,42 +430,42 @@ class Pool(OpenMPOp):
...
@@ -426,42 +430,42 @@ class Pool(OpenMPOp):
if (
%(ignore_border)
s)
if (
%(ignore_border)
s)
{
{
// '/' in C is different from '/' in python
// '/' in C is different from '/' in python
if (r -
%(ws0)
s
< 0)
if (r -
ws0
< 0)
{
{
z_r = 0;
z_r = 0;
}
}
else
else
{
{
z_r = (r -
%(ws0)
s) /
%(st0)
s
+ 1;
z_r = (r -
ws0) / st0
+ 1;
}
}
if (c -
%(ws1)
s
< 0)
if (c -
ws1
< 0)
{
{
z_c = 0;
z_c = 0;
}
}
else
else
{
{
z_c = (c -
%(ws1)
s) /
%(st1)
s
+ 1;
z_c = (c -
ws1) / st1
+ 1;
}
}
}
}
else
else
{
{
// decide how many rows the output has
// decide how many rows the output has
if (
%(st0)
s >=
%(ws0)
s
)
if (
st0 >= ws0
)
{
{
z_r = (r - 1) /
%(st0)
s
+ 1;
z_r = (r - 1) /
st0
+ 1;
}
}
else
else
{
{
z_r = std::max(0, (r - 1 -
%(ws0)
s +
%(st0)
s) /
%(st0)
s
) + 1;
z_r = std::max(0, (r - 1 -
ws0 + st0) / st0
) + 1;
}
}
// decide how many columns the output has
// decide how many columns the output has
if (
%(st1)
s >=
%(ws1)
s
)
if (
st1 >= ws1
)
{
{
z_c = (c - 1) /
%(st1)
s
+ 1;
z_c = (c - 1) /
st1
+ 1;
}
}
else
else
{
{
z_c = std::max(0, (c - 1 -
%(ws1)
s +
%(st0)
s) /
%(st1)
s
) + 1;
z_c = std::max(0, (c - 1 -
ws1 + st0) / st1
) + 1;
}
}
assert(z_r > 0);
assert(z_r > 0);
assert(z_c > 0);
assert(z_c > 0);
...
@@ -494,30 +498,30 @@ class Pool(OpenMPOp):
...
@@ -494,30 +498,30 @@ class Pool(OpenMPOp):
int b = t
%%
PyArray_DIMS(
%(x)
s)[0];
int b = t
%%
PyArray_DIMS(
%(x)
s)[0];
int k = t / PyArray_DIMS(
%(x)
s)[0];
int k = t / PyArray_DIMS(
%(x)
s)[0];
for(int i=0; i < z_r; i++){
for(int i=0; i < z_r; i++){
r_st = i *
%(st0)
s
;
r_st = i *
st0
;
r_end = r_st +
%(ws0)
s
;
r_end = r_st +
ws0
;
// skip the padding
// skip the padding
r_st = r_st <
%(pd0)
s ?
%(pd0)
s
: r_st;
r_st = r_st <
pd0 ? pd0
: r_st;
r_end = r_end > (r -
%(pd0)
s) ? r -
%(pd0)
s
: r_end;
r_end = r_end > (r -
pd0) ? r - pd0
: r_end;
// from padded_img space to img space
// from padded_img space to img space
r_st -=
%(pd0)
s
;
r_st -=
pd0
;
r_end -=
%(pd0)
s
;
r_end -=
pd0
;
// handle the case where no padding, ignore border is True
// handle the case where no padding, ignore border is True
if (
%(ignore_border)
s)
if (
%(ignore_border)
s)
{
{
r_end = r_end > r ? r : r_end;
r_end = r_end > r ? r : r_end;
}
}
for(int j=0; j<z_c; j++){
for(int j=0; j<z_c; j++){
c_st = j *
%(st1)
s
;
c_st = j *
st1
;
c_end = c_st +
%(ws1)
s
;
c_end = c_st +
ws1
;
// skip the padding
// skip the padding
c_st = c_st <
%(pd1)
s ?
%(pd1)
s
: c_st;
c_st = c_st <
pd1 ? pd1
: c_st;
c_end = c_end > (c -
%(pd1)
s) ? c -
%(pd1)
s
: c_end;
c_end = c_end > (c -
pd1) ? c - pd1
: c_end;
dtype_
%(z)
s * z = (
dtype_
%(z)
s * z = (
(dtype_
%(z)
s*)(PyArray_GETPTR4(
%(z)
s, b, k, i, j)));
(dtype_
%(z)
s*)(PyArray_GETPTR4(
%(z)
s, b, k, i, j)));
// change coordinates from padding_img space into img space
// change coordinates from padding_img space into img space
c_st -=
%(pd1)
s
;
c_st -=
pd1
;
c_end -=
%(pd1)
s
;
c_end -=
pd1
;
// handle the case where no padding, ignore border is True
// handle the case where no padding, ignore border is True
if (
%(ignore_border)
s)
if (
%(ignore_border)
s)
{
{
...
@@ -559,7 +563,7 @@ class Pool(OpenMPOp):
...
@@ -559,7 +563,7 @@ class Pool(OpenMPOp):
"""
"""
elif
self
.
mode
==
'average_inc_pad'
and
self
.
ignore_border
:
elif
self
.
mode
==
'average_inc_pad'
and
self
.
ignore_border
:
ccode
+=
"""
ccode
+=
"""
z[0] = collector / (
%(ws0)
s *
%(ws1)
s
);
z[0] = collector / (
ws0 * ws1
);
"""
"""
else
:
else
:
ccode
+=
"""
ccode
+=
"""
...
@@ -784,9 +788,6 @@ class MaxPoolGrad(PoolGrad):
...
@@ -784,9 +788,6 @@ class MaxPoolGrad(PoolGrad):
gx
,
=
out
gx
,
=
out
fail
=
sub
[
'fail'
]
fail
=
sub
[
'fail'
]
ignore_border
=
int
(
self
.
ignore_border
)
ignore_border
=
int
(
self
.
ignore_border
)
ws0
,
ws1
=
ws
st0
,
st1
=
stride
pd0
,
pd1
=
pad
if
self
.
openmp
:
if
self
.
openmp
:
omp_parallel
=
'#pragma omp parallel for private(r_st, r_end, c_st, c_end, maximum) schedule(static)'
omp_parallel
=
'#pragma omp parallel for private(r_st, r_end, c_st, c_end, maximum) schedule(static)'
else
:
else
:
...
@@ -816,14 +817,22 @@ class MaxPoolGrad(PoolGrad):
...
@@ -816,14 +817,22 @@ class MaxPoolGrad(PoolGrad):
PyErr_SetString(PyExc_ValueError, "gz must be a 4d ndarray");
PyErr_SetString(PyExc_ValueError, "gz must be a 4d ndarray");
%(fail)
s;
%(fail)
s;
}
}
// Getting ws, stride and pad
int ws0, ws1, st0, st1, pd0, pd1;
ws0 = *((npy_intp*)PyArray_GETPTR1(
%(ws)
s, 0));
ws1 = *((npy_intp*)PyArray_GETPTR1(
%(ws)
s, 1));
st0 = *((npy_intp*)PyArray_GETPTR1(
%(stride)
s, 0));
st1 = *((npy_intp*)PyArray_GETPTR1(
%(stride)
s, 1));
pd0 = *((npy_intp*)PyArray_GETPTR1(
%(pad)
s, 0));
pd1 = *((npy_intp*)PyArray_GETPTR1(
%(pad)
s, 1));
int z_r, z_c;
int z_r, z_c;
z_r = PyArray_DIMS(
%(z)
s)[2];
z_r = PyArray_DIMS(
%(z)
s)[2];
z_c = PyArray_DIMS(
%(z)
s)[3];
z_c = PyArray_DIMS(
%(z)
s)[3];
int r, c; // shape of the padded_input
int r, c; // shape of the padded_input
r = PyArray_DIMS(
%(x)
s)[2];
r = PyArray_DIMS(
%(x)
s)[2];
c = PyArray_DIMS(
%(x)
s)[3];
c = PyArray_DIMS(
%(x)
s)[3];
r +=
%(pd0)
s
* 2;
r +=
pd0
* 2;
c +=
%(pd1)
s
* 2;
c +=
pd1
* 2;
// allocating memory for gx
// allocating memory for gx
if ((!
%(gx)
s)
if ((!
%(gx)
s)
|| !PyArray_ISCONTIGUOUS(
%(gx)
s)
|| !PyArray_ISCONTIGUOUS(
%(gx)
s)
...
@@ -849,23 +858,23 @@ class MaxPoolGrad(PoolGrad):
...
@@ -849,23 +858,23 @@ class MaxPoolGrad(PoolGrad):
int b = t
%%
PyArray_DIMS(
%(x)
s)[0];
int b = t
%%
PyArray_DIMS(
%(x)
s)[0];
int k = t / PyArray_DIMS(
%(x)
s)[0];
int k = t / PyArray_DIMS(
%(x)
s)[0];
for(int i=0; i < z_r; i++){
for(int i=0; i < z_r; i++){
r_st = i *
%(st0)
s
;
r_st = i *
st0
;
r_end = r_st +
%(ws0)
s
;
r_end = r_st +
ws0
;
// skip the padding
// skip the padding
r_st = r_st <
%(pd0)
s ?
%(pd0)
s
: r_st;
r_st = r_st <
pd0 ? pd0
: r_st;
r_end = r_end > (r -
%(pd0)
s) ? r -
%(pd0)
s
: r_end;
r_end = r_end > (r -
pd0) ? r - pd0
: r_end;
// from padded_img space to img space
// from padded_img space to img space
r_st -=
%(pd0)
s
;
r_st -=
pd0
;
r_end -=
%(pd0)
s
;
r_end -=
pd0
;
for(int j=0; j<z_c; j++){
for(int j=0; j<z_c; j++){
c_st = j *
%(st1)
s
;
c_st = j *
st1
;
c_end = c_st +
%(ws1)
s
;
c_end = c_st +
ws1
;
// skip the padding
// skip the padding
c_st = c_st <
%(pd1)
s ?
%(pd1)
s
: c_st;
c_st = c_st <
pd1 ? pd1
: c_st;
c_end = c_end > (c -
%(pd1)
s) ? c -
%(pd1)
s
: c_end;
c_end = c_end > (c -
pd1) ? c - pd1
: c_end;
// change coordinates from padding_img space into img space
// change coordinates from padding_img space into img space
c_st -=
%(pd1)
s
;
c_st -=
pd1
;
c_end -=
%(pd1)
s
;
c_end -=
pd1
;
// the maximum value
// the maximum value
maximum = ((dtype_
%(z)
s*)(PyArray_GETPTR4(
%(z)
s,b,k,i,j)))[0];
maximum = ((dtype_
%(z)
s*)(PyArray_GETPTR4(
%(z)
s,b,k,i,j)))[0];
// the gradient corresponding to this maximum value in z
// the gradient corresponding to this maximum value in z
...
@@ -1096,14 +1105,19 @@ class DownsampleFactorMaxGradGrad(OpenMPOp):
...
@@ -1096,14 +1105,19 @@ class DownsampleFactorMaxGradGrad(OpenMPOp):
z
,
=
out
# the grad of grad
z
,
=
out
# the grad of grad
fail
=
sub
[
'fail'
]
fail
=
sub
[
'fail'
]
ignore_border
=
int
(
self
.
ignore_border
)
ignore_border
=
int
(
self
.
ignore_border
)
ws0
,
ws1
=
ws
st0
,
st1
=
stride
pd0
,
pd1
=
pad
if
self
.
openmp
:
if
self
.
openmp
:
omp_parallel
=
'#pragma omp parallel for private(r_st, r_end, c_st, c_end, maximum) schedule(static)'
omp_parallel
=
'#pragma omp parallel for private(r_st, r_end, c_st, c_end, maximum) schedule(static)'
else
:
else
:
omp_parallel
=
''
omp_parallel
=
''
return
"""
return
"""
// Getting ws, stride and pad
int ws0, ws1, st0, st1, pd0, pd1;
ws0 = *((npy_intp*)PyArray_GETPTR1(
%(ws)
s, 0));
ws1 = *((npy_intp*)PyArray_GETPTR1(
%(ws)
s, 1));
st0 = *((npy_intp*)PyArray_GETPTR1(
%(stride)
s, 0));
st1 = *((npy_intp*)PyArray_GETPTR1(
%(stride)
s, 1));
pd0 = *((npy_intp*)PyArray_GETPTR1(
%(pad)
s, 0));
pd1 = *((npy_intp*)PyArray_GETPTR1(
%(pad)
s, 1));
int z_typenum = PyArray_ObjectType((PyObject*)
%(maxout)
s, 0);
int z_typenum = PyArray_ObjectType((PyObject*)
%(maxout)
s, 0);
int z_r, z_c;
int z_r, z_c;
z_r = PyArray_DIMS(
%(maxout)
s)[2];
z_r = PyArray_DIMS(
%(maxout)
s)[2];
...
@@ -1111,8 +1125,8 @@ class DownsampleFactorMaxGradGrad(OpenMPOp):
...
@@ -1111,8 +1125,8 @@ class DownsampleFactorMaxGradGrad(OpenMPOp):
int r, c; // shape of the padded_input
int r, c; // shape of the padded_input
r = PyArray_DIMS(
%(x)
s)[2];
r = PyArray_DIMS(
%(x)
s)[2];
c = PyArray_DIMS(
%(x)
s)[3];
c = PyArray_DIMS(
%(x)
s)[3];
r +=
%(pd0)
s
* 2;
r +=
pd0
* 2;
c +=
%(pd1)
s
* 2;
c +=
pd1
* 2;
// allocating memory for output
// allocating memory for output
if ((!
%(z)
s)
if ((!
%(z)
s)
|| !PyArray_ISCONTIGUOUS(
%(z)
s)
|| !PyArray_ISCONTIGUOUS(
%(z)
s)
...
@@ -1136,23 +1150,23 @@ class DownsampleFactorMaxGradGrad(OpenMPOp):
...
@@ -1136,23 +1150,23 @@ class DownsampleFactorMaxGradGrad(OpenMPOp):
int b = t
%%
PyArray_DIMS(
%(x)
s)[0];
int b = t
%%
PyArray_DIMS(
%(x)
s)[0];
int k = t / PyArray_DIMS(
%(x)
s)[0];
int k = t / PyArray_DIMS(
%(x)
s)[0];
for(int i=0; i < z_r; i++){
for(int i=0; i < z_r; i++){
r_st = i *
%(st0)
s
;
r_st = i *
st0
;
r_end = r_st +
%(ws0)
s
;
r_end = r_st +
ws0
;
// skip the padding
// skip the paddin
_
g
r_st = r_st <
%(pd0)
s ?
%(pd0)
s
: r_st;
r_st = r_st <
pd0 ? pd0
: r_st;
r_end = r_end > (r -
%(pd0)
s) ? r -
%(pd0)
s
: r_end;
r_end = r_end > (r -
pd0) ? r - pd0
: r_end;
// from padded_img space to img space
// from padded_img space to img space
r_st -=
%(pd0)
s
;
r_st -=
pd0
;
r_end -=
%(pd0)
s
;
r_end -=
pd0
;
for(int j=0; j<z_c; j++){
for(int j=0; j<z_c; j++){
c_st = j *
%(st1)
s
;
c_st = j *
st1
;
c_end = c_st +
%(ws1)
s
;
c_end = c_st +
ws1
;
// skip the padding
// skip the padding
c_st = c_st <
%(pd1)
s ?
%(pd1)
s
: c_st;
c_st = c_st <
pd1 ? pd1
: c_st;
c_end = c_end > (c -
%(pd1)
s) ? c -
%(pd1)
s
: c_end;
c_end = c_end > (c -
pd1) ? c - pd1
: c_end;
// from padding_img space into img space
// from padding_img space into img space
c_st -=
%(pd1)
s
;
c_st -=
pd1
;
c_end -=
%(pd1)
s
;
c_end -=
pd1
;
// the maximum value
// the maximum value
maximum = ((dtype_
%(maxout)
s*)(PyArray_GETPTR4(
%(maxout)
s,b,k,i,j)))[0];
maximum = ((dtype_
%(maxout)
s*)(PyArray_GETPTR4(
%(maxout)
s,b,k,i,j)))[0];
// z at this position
// z at this position
...
...
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