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
be12a5cf
提交
be12a5cf
authored
12月 15, 2014
作者:
Arnaud Bergeron
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Get rid of typeConstructor in Scan.
上级
ba45997f
隐藏空白字符变更
内嵌
并排
正在显示
5 个修改的文件
包含
11 行增加
和
49 行删除
+11
-49
opt.py
theano/sandbox/cuda/opt.py
+3
-13
opt.py
theano/sandbox/gpuarray/opt.py
+2
-4
test_scan.py
theano/sandbox/gpuarray/tests/test_scan.py
+1
-0
scan_op.py
theano/scan_module/scan_op.py
+2
-26
scan_opt.py
theano/scan_module/scan_opt.py
+3
-6
没有找到文件。
theano/sandbox/cuda/opt.py
浏览文件 @
be12a5cf
...
...
@@ -2000,12 +2000,6 @@ def local_gpu_extract_diagonal(node):
gpu_from_host
(
diag_node
.
inputs
[
0
]))]
return
False
def
typeConstructor
(
broadcastable
,
dtype
):
if
dtype
==
'float32'
:
return
CudaNdarrayType
(
broadcastable
=
broadcastable
)
else
:
return
tensor
.
TensorType
(
broadcastable
=
broadcastable
,
dtype
=
dtype
)
@register_opt
(
'scan'
)
@local_optimizer
([
gpu_from_host
,
scan_op
.
Scan
])
def
gpuScanOptimization
(
node
):
...
...
@@ -2065,9 +2059,7 @@ def gpuScanOptimization(node):
nw_op
=
scan_op
.
Scan
(
scan_ins
,
scan_outs
,
info
,
typeConstructor
=
typeConstructor
)
.
make_node
(
*
nw_ins
)
info
)
.
make_node
(
*
nw_ins
)
_outputs
=
nw_op
.
outputs
return
_outputs
...
...
@@ -2113,8 +2105,7 @@ def gpuScanOptimization(node):
_outputs
=
scan_op
.
Scan
(
scan_ins
,
scan_outs
,
info
,
typeConstructor
=
typeConstructor
)
.
make_node
(
*
nw_ins
)
.
outputs
info
)
.
make_node
(
*
nw_ins
)
.
outputs
outputs
=
[]
for
x
,
y
in
zip
(
_outputs
,
node
.
outputs
):
if
isinstance
(
y
.
type
,
CudaNdarrayType
):
...
...
@@ -2126,8 +2117,7 @@ def gpuScanOptimization(node):
optdb
.
register
(
'gpu_scanOp_make_inplace'
,
scan_opt
.
ScanInplaceOptimizer
(
typeConstructor
=
typeConstructor
,
gpu_flag
=
True
),
scan_opt
.
ScanInplaceOptimizer
(
gpu_flag
=
True
),
75
,
'gpu'
,
'fast_run'
,
...
...
theano/sandbox/gpuarray/opt.py
浏览文件 @
be12a5cf
...
...
@@ -716,13 +716,11 @@ def local_scan_to_gpua(node):
_cmodule_key
=
gof
.
CLinker
()
.
cmodule_key_
(
local_fgraph
,
[])
info
[
'gpu_hash'
]
=
hash
(
_cmodule_key
)
nw_op
=
scan_op
.
Scan
(
scan_ins
,
scan_outs
,
info
,
typeConstructor
=
GpuArrayType
)
.
make_node
(
*
nw_ins
)
nw_op
=
scan_op
.
Scan
(
scan_ins
,
scan_outs
,
info
)
.
make_node
(
*
nw_ins
)
return
nw_op
.
outputs
optdb
.
register
(
'gpua_scanOp_make_inplace'
,
scan_opt
.
ScanInplaceOptimizer
(
typeConstructor
=
GpuArrayType
,
gpua_flag
=
True
),
scan_opt
.
ScanInplaceOptimizer
(
gpua_flag
=
True
),
75
,
'gpua'
,
'fast_run'
,
...
...
theano/sandbox/gpuarray/tests/test_scan.py
浏览文件 @
be12a5cf
...
...
@@ -15,6 +15,7 @@ from theano.sandbox.gpuarray.tests.test_basic_ops import mode_with_gpu
class
T_Scan
(
TestCase
):
def
setUp
(
self
):
utt
.
seed_rng
()
super
(
T_Scan
,
self
)
.
setUp
()
def
test_one_sequence_one_output_weights_gpu1
(
self
):
def
f_rnn
(
u_t
,
x_tm1
,
W_in
,
W
):
...
...
theano/scan_module/scan_op.py
浏览文件 @
be12a5cf
...
...
@@ -49,7 +49,6 @@ class Scan(PureOp):
inputs
,
outputs
,
info
,
typeConstructor
=
None
,
):
"""
:param inputs: inputs of the inner function of scan
...
...
@@ -58,21 +57,6 @@ class Scan(PureOp):
the scan op (like number of different types of
arguments, name, mode, if it should run on GPU or
not, etc.)
:param typeConstructor: function that constructs an equivalent
to Theano TensorType
Note: ``typeConstructor`` had been added to refactor how
Theano deals with the GPU. If it runs on the GPU, scan needs
to construct certain outputs (those who reside in the GPU
memory) as the GPU-specific type. However we can not import
gpu code in this file (as it is in sandbox, and not available
on each machine) so the workaround is that the GPU
optimization passes to the constructor of this class a
function that is able to construct a GPU type. This way the
class Scan does not need to be aware of the details for the
GPU, it just constructs any tensor using this function (which
by default constructs normal tensors).
"""
if
'gpua'
not
in
info
:
info
[
'gpua'
]
=
False
...
...
@@ -88,19 +72,13 @@ class Scan(PureOp):
self
.
output_types
=
[]
idx
=
0
jdx
=
0
tensorConstructor
=
lambda
broadcastable
,
dtype
:
TensorType
(
broadcastable
=
broadcastable
,
dtype
=
dtype
)
if
typeConstructor
is
None
:
typeConstructor
=
tensorConstructor
while
idx
<
self
.
n_mit_mot_outs
:
# Not that for mit_mot there are several output slices per
# output sequence
o
=
outputs
[
idx
]
self
.
output_types
.
append
(
typeConstructor
(
broadcastable
=
(
False
,)
+
o
.
type
.
broadcastable
,
dtype
=
o
.
type
.
dtype
))
o
.
type
.
clone
(
broadcastable
=
(
False
,)
+
o
.
type
.
broadcastable
))
idx
+=
len
(
self
.
mit_mot_out_slices
[
jdx
])
jdx
+=
1
...
...
@@ -110,9 +88,7 @@ class Scan(PureOp):
for
o
in
outputs
[
idx
:
end
]:
self
.
output_types
.
append
(
typeConstructor
(
broadcastable
=
(
False
,)
+
o
.
type
.
broadcastable
,
dtype
=
o
.
type
.
dtype
))
o
.
type
.
clone
(
broadcastable
=
(
False
,)
+
o
.
type
.
broadcastable
))
# shared outputs + possibly the ending condition
for
o
in
outputs
[
end
:]:
...
...
theano/scan_module/scan_opt.py
浏览文件 @
be12a5cf
...
...
@@ -916,9 +916,8 @@ class PushOutScanOutput(gof.Optimizer):
class
ScanInplaceOptimizer
(
Optimizer
):
"""Graph optimizer for Scan(makes it run inplace)"""
def
__init__
(
self
,
typeConstructor
=
None
,
gpu_flag
=
False
,
gpua_flag
=
False
):
def
__init__
(
self
,
gpu_flag
=
False
,
gpua_flag
=
False
):
Optimizer
.
__init__
(
self
)
self
.
typeConstructor
=
typeConstructor
self
.
gpu_flag
=
gpu_flag
self
.
gpua_flag
=
gpua_flag
...
...
@@ -960,8 +959,7 @@ class ScanInplaceOptimizer(Optimizer):
inputs
=
ls_begin
+
ls
+
ls_end
new_op
=
scan_op
.
Scan
(
op
.
inputs
,
op
.
outputs
,
info
,
typeConstructor
=
self
.
typeConstructor
)
info
)
# Do not call make_node for test_value
new_outs
=
new_op
(
*
inputs
,
**
dict
(
return_list
=
True
))
...
...
@@ -2087,8 +2085,7 @@ scan_eqopt2 = theano.gof.EquilibriumDB()
optdb
.
register
(
'scan_eqopt1'
,
scan_eqopt1
,
.
1
,
'fast_run'
,
'scan'
)
optdb
.
register
(
'scan_eqopt2'
,
scan_eqopt2
,
1.6
,
'fast_run'
,
'scan'
)
optdb
.
register
(
'scanOp_make_inplace'
,
ScanInplaceOptimizer
(
typeConstructor
=
None
,
gpu_flag
=
False
),
ScanInplaceOptimizer
(),
75
,
'fast_run'
,
'inplace'
,
...
...
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