Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
PaddlePaddle
X2Paddle
提交
4c29d6df
X
X2Paddle
项目概览
PaddlePaddle
/
X2Paddle
1 年多 前同步成功
通知
328
Star
698
Fork
167
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
26
列表
看板
标记
里程碑
合并请求
4
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
X
X2Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
26
Issue
26
列表
看板
标记
里程碑
合并请求
4
合并请求
4
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
未验证
提交
4c29d6df
编写于
5年前
作者:
J
Jason
提交者:
GitHub
5年前
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #149 from jiangjiajun/develop
add optimization for scale
上级
a3275d80
dd9e3172
develop
OliverLPH-patch-1
bert
branch-1.6-unstable
develop_0925
develop_for_issue_386
develop_jason
fixed_models
github/fork/Channingss/add_op
github/fork/Channingss/input_shape
github/fork/Channingss/onnx_shape_infer
paddle-1.6
paddle2onnx
release-0.5
release-0.8
release-0.9
release-1.0
release-1.1
release-1.2
release-1.3
release-1.4
revert-674-fix-caffe-pooling-convert-bug
syf
v1.4.1
v1.4.0
v1.3.9
v1.3.8
v1.3.7
v1.3.6
v1.3.5
v1.3.4
v1.3.3
v1.3.2
v1.3.1
v1.3.0
v1.2.3
v1.2.2
v1.2.1
v1.2.0
v1.1.0
v1.0.2
v1.0.1
v1.0.0rc1
v1.0.0rc0
v0.8.9
v0.8.8
v0.8.7
v0.8.6
v0.8.5
v0.8.4
v0.8.3
v0.7
v0.6
变更
2
显示空白变更内容
内联
并排
Showing
2 changed file
with
226 addition
and
5 deletion
+226
-5
x2paddle/convert.py
x2paddle/convert.py
+5
-2
x2paddle/optimizer/tf_optimizer.py
x2paddle/optimizer/tf_optimizer.py
+221
-3
未找到文件。
x2paddle/convert.py
浏览文件 @
4c29d6df
...
...
@@ -106,8 +106,11 @@ def tf2paddle(model_path,
# optimizer below is experimental
optimizer
.
merge_activation
()
optimizer
.
merge_bias
()
optimizer
.
merge_batch_norm
()
optimizer
.
merge_prelu
()
optimizer
.
optimize_sub_graph
()
# optimizer.merge_batch_norm()
# optimizer.merge_prelu()
else
:
mapper
=
TFOpMapperNHWC
(
model
)
optimizer
=
TFOptimizer
(
mapper
)
...
...
This diff is collapsed.
Click to expand it.
x2paddle/optimizer/tf_optimizer.py
浏览文件 @
4c29d6df
...
...
@@ -20,6 +20,15 @@ import numpy
import
copy
as
cp
def
exist_act
(
node
):
for
layer
in
node
.
fluid_code
.
layers
:
if
layer
.
param_attr
is
not
None
:
act
=
layer
.
param_attr
.
get
(
"act"
,
None
)
if
act
is
not
None
:
return
True
return
False
class
TFOptimizer
(
object
):
activation_ops
=
{
'Relu'
:
'relu'
,
...
...
@@ -353,6 +362,12 @@ class TFOptimizer(object):
node
.
fluid_code
.
layers
[
-
2
].
output
=
name
del
node
.
fluid_code
.
layers
[
-
1
]
def
optimize_sub_graph
(
self
):
self
.
merge_batch_norm
()
self
.
merge_prelu
()
self
.
merge_scale
()
self
.
merge_affine_channel
()
def
merge_batch_norm
(
self
):
for
i
,
name
in
enumerate
(
self
.
graph
.
topo_sort
):
node
=
self
.
graph
.
get_node
(
name
)
...
...
@@ -368,6 +383,10 @@ class TFOptimizer(object):
is_batch_norm
=
False
continue
if
exist_act
(
in_nodes0
[
0
])
or
exist_act
(
in_nodes0
[
1
]):
is_batch_norm
=
False
continue
in_nodes1
=
[
self
.
graph
.
get_node
(
in_name
)
for
in_name
in
in_nodes0
[
0
].
inputs
...
...
@@ -382,11 +401,17 @@ class TFOptimizer(object):
if
in_nodes1
[
1
].
layer_type
!=
"Mul"
:
is_batch_norm
=
False
continue
if
exist_act
(
in_nodes1
[
1
]):
is_batch_norm
=
False
continue
if
in_nodes2
[
0
].
layer_type
!=
"Const"
or
in_nodes2
[
1
].
layer_type
!=
"Mul"
:
is_batch_norm
=
False
continue
if
exist_act
(
in_nodes2
[
1
]):
is_batch_norm
=
False
continue
in_nodes3
=
[
self
.
graph
.
get_node
(
in_name
)
...
...
@@ -410,6 +435,9 @@ class TFOptimizer(object):
if
in_nodes5
.
layer_type
!=
"Add"
:
is_batch_norm
=
False
continue
if
exist_act
(
in_nodes5
):
is_batch_norm
=
False
continue
in_nodes6
=
[
self
.
graph
.
get_node
(
in_name
)
for
in_name
in
in_nodes5
.
inputs
...
...
@@ -485,10 +513,9 @@ class TFOptimizer(object):
if
is_batch_norm
:
index
=
in_nodes1
[
0
].
outputs
.
index
(
in_nodes0
[
0
].
layer_name
)
del
in_nodes1
[
0
].
outputs
[
index
]
in_nodes1
[
0
].
outputs
[
index
]
=
node
.
layer_name
node
.
layer_type
=
"FusedBatchNorm"
node
.
inputs
=
[
in_nodes1
[
0
].
layer_name
]
node
.
outputs
=
node
.
outputs
act
=
node
.
fluid_code
.
layers
[
-
1
].
param_attr
.
get
(
"act"
,
None
)
node
.
fluid_code
.
clear
()
attr
=
{
...
...
@@ -522,6 +549,9 @@ class TFOptimizer(object):
continue
is_prelu
=
True
if
node
.
layer_type
==
"Add"
:
if
exist_act
(
node
):
is_prelu
=
False
continue
in_nodes0
=
[
self
.
graph
.
get_node
(
in_name
)
for
in_name
in
node
.
inputs
]
...
...
@@ -529,6 +559,10 @@ class TFOptimizer(object):
1
].
layer_type
!=
"Mul"
:
is_prelu
=
False
continue
if
exist_act
(
in_nodes0
[
1
]):
is_prelu
=
False
continue
if
len
(
in_nodes0
[
0
].
outputs
)
!=
1
or
len
(
in_nodes0
[
1
].
outputs
)
!=
1
:
is_prelu
=
False
...
...
@@ -546,6 +580,9 @@ class TFOptimizer(object):
if
in_nodes2
[
0
].
layer_type
!=
"Mul"
:
is_prelu
=
False
continue
if
exist_act
(
in_nodes2
[
0
]):
is_prelu
=
False
continue
if
len
(
in_nodes2
[
1
].
outputs
)
!=
1
or
len
(
in_nodes2
[
0
].
outputs
)
!=
1
:
is_prelu
=
False
...
...
@@ -559,6 +596,9 @@ class TFOptimizer(object):
1
].
layer_type
!=
"Sub"
:
is_prelu
=
False
continue
if
exist_act
(
in_nodes3
[
1
]):
is_prelu
=
False
continue
if
len
(
in_nodes3
[
0
].
outputs
)
!=
1
or
len
(
in_nodes3
[
1
].
outputs
)
!=
1
:
is_prelu
=
False
...
...
@@ -638,10 +678,10 @@ class TFOptimizer(object):
del
in_nodes1
.
outputs
[
index
]
index
=
in_nodes1
.
outputs
.
index
(
in_nodes4
[
1
].
layer_name
)
del
in_nodes1
.
outputs
[
index
]
in_nodes1
.
outputs
.
append
(
node
.
layer_name
)
node
.
layer_type
=
"Prelu"
node
.
inputs
=
[
in_nodes1
.
layer_name
]
node
.
outputs
=
node
.
outputs
act
=
node
.
fluid_code
.
layers
[
-
1
].
param_attr
.
get
(
"act"
,
None
)
node
.
fluid_code
.
clear
()
attr
=
{
...
...
@@ -660,3 +700,181 @@ class TFOptimizer(object):
del
self
.
graph
.
node_map
[
in_nodes2
[
1
].
layer_name
]
del
self
.
graph
.
node_map
[
in_nodes3
[
1
].
layer_name
]
del
self
.
graph
.
node_map
[
in_nodes4
[
1
].
layer_name
]
def
merge_scale
(
self
):
for
i
,
name
in
enumerate
(
self
.
graph
.
topo_sort
):
node
=
self
.
graph
.
get_node
(
name
)
if
node
is
None
:
continue
is_scale
=
True
if
node
.
layer_type
==
"Sub"
:
in_nodes0
=
[
self
.
graph
.
get_node
(
in_name
)
for
in_name
in
node
.
inputs
]
if
in_nodes0
[
0
].
layer_type
!=
"Mul"
or
in_nodes0
[
1
].
layer_type
!=
"Const"
or
in_nodes0
[
1
].
value
.
size
!=
1
:
is_scale
=
False
continue
if
exist_act
(
in_nodes0
[
0
]):
is_scale
=
False
continue
if
len
(
in_nodes0
[
0
].
outputs
)
!=
1
or
len
(
in_nodes0
[
1
].
outputs
)
!=
1
:
is_scale
=
False
continue
in_nodes1
=
[
self
.
graph
.
get_node
(
in_name
)
for
in_name
in
in_nodes0
[
0
].
inputs
]
if
in_nodes1
[
0
].
layer_type
!=
"Const"
or
in_nodes1
[
1
].
layer_type
!=
"RealDiv"
or
in_nodes1
[
0
].
value
.
size
!=
1
:
is_scale
=
False
continue
if
exist_act
(
in_nodes1
[
1
]):
is_scale
=
False
continue
if
len
(
in_nodes1
[
0
].
outputs
)
!=
1
or
len
(
in_nodes1
[
1
].
outputs
)
!=
1
:
is_scale
=
False
continue
in_nodes2
=
[
self
.
graph
.
get_node
(
in_name
)
for
in_name
in
in_nodes1
[
1
].
inputs
]
if
in_nodes2
[
1
].
layer_type
!=
"Const"
or
in_nodes2
[
1
].
value
.
size
!=
1
:
is_scale
=
False
continue
if
is_scale
:
in_node
=
self
.
graph
.
get_node
(
in_nodes1
[
1
].
inputs
[
0
])
index
=
in_node
.
outputs
.
index
(
in_nodes1
[
1
].
layer_name
)
in_node
.
outputs
[
index
]
=
node
.
layer_name
node
.
layer_type
=
"Scale"
node
.
inputs
=
[
in_node
.
layer_name
]
scale
=
1.0
/
in_nodes2
[
1
].
value
*
in_nodes1
[
0
].
value
act
=
None
if
node
.
fluid_code
.
layers
[
0
].
param_attr
is
not
None
:
act
=
node
.
fluid_code
.
layers
[
0
].
param_attr
.
get
(
"act"
,
None
)
node
.
fluid_code
.
clear
()
attr
=
{
"scale"
:
scale
,
"bias"
:
in_nodes0
[
1
].
value
,
"bias_after_scale"
:
True
,
"act"
:
act
}
node
.
fluid_code
.
add_layer
(
"scale"
,
inputs
=
in_node
,
output
=
node
,
param_attr
=
attr
)
del
self
.
graph
.
node_map
[
in_nodes0
[
0
].
layer_name
]
del
self
.
graph
.
node_map
[
in_nodes0
[
1
].
layer_name
]
del
self
.
graph
.
node_map
[
in_nodes1
[
0
].
layer_name
]
del
self
.
graph
.
node_map
[
in_nodes1
[
1
].
layer_name
]
del
self
.
graph
.
node_map
[
in_nodes2
[
1
].
layer_name
]
def
merge_affine_channel
(
self
):
for
i
,
name
in
enumerate
(
self
.
graph
.
topo_sort
):
node
=
self
.
graph
.
get_node
(
name
)
if
node
is
None
:
continue
is_affine_channel
=
True
if
node
.
layer_type
==
"RealDiv"
:
in_nodes0
=
[
self
.
graph
.
get_node
(
in_name
)
for
in_name
in
node
.
inputs
]
bias_add
=
True
if
(
in_nodes0
[
0
].
layer_type
!=
"Sub"
and
in_nodes0
[
0
].
layer_type
!=
"Add"
)
or
in_nodes0
[
1
].
layer_type
!=
"Const"
or
len
(
in_nodes0
[
1
].
value
.
shape
)
!=
3
:
is_affine_channel
=
False
continue
if
in_nodes0
[
0
].
layer_type
==
"Sub"
:
bias_add
=
False
if
exist_act
(
in_nodes0
[
0
]):
is_affine_channel
=
False
continue
if
len
(
in_nodes0
[
0
].
outputs
)
!=
1
or
len
(
in_nodes0
[
1
].
outputs
)
!=
1
:
is_affine_channel
=
False
continue
in_nodes1
=
[
self
.
graph
.
get_node
(
in_name
)
for
in_name
in
in_nodes0
[
0
].
inputs
]
if
len
(
in_nodes1
[
0
].
out_shapes
[
0
]
)
!=
4
or
in_nodes1
[
1
].
layer_type
!=
"Const"
or
len
(
in_nodes1
[
1
].
value
.
shape
)
!=
3
:
is_affine_channel
=
False
continue
if
len
(
in_nodes1
[
1
].
outputs
)
!=
1
:
is_affine_channel
=
False
continue
channel
=
in_nodes1
[
0
].
out_shapes
[
0
][
-
1
]
if
channel
<
0
or
channel
!=
in_nodes0
[
1
].
value
.
size
or
channel
!=
in_nodes1
[
1
].
value
.
size
:
is_affine_channel
=
False
continue
if
in_nodes0
[
1
].
out_shapes
[
0
][
-
1
]
!=
in_nodes0
[
1
].
value
.
size
or
in_nodes1
[
1
].
out_shapes
[
0
][
-
1
]
!=
in_nodes1
[
1
].
value
.
size
:
is_affine_channel
=
False
continue
if
is_affine_channel
:
in_node
=
in_nodes1
[
0
]
index
=
in_node
.
outputs
.
index
(
in_nodes0
[
0
].
layer_name
)
in_node
.
outputs
[
index
]
=
node
.
layer_name
node
.
layer_type
=
"AffineChannel"
node
.
inputs
=
[
in_node
.
layer_name
]
scale
=
1.0
/
in_nodes0
[
1
].
value
.
flatten
()
bias
=
in_nodes1
[
1
].
value
.
flatten
(
)
/
in_nodes0
[
1
].
value
.
flatten
()
if
not
bias_add
:
bias
*=
-
1.0
self
.
op_mapper
.
weights
[
node
.
layer_name
+
"_scale"
]
=
scale
self
.
op_mapper
.
weights
[
node
.
layer_name
+
"_bias"
]
=
bias
act
=
None
if
node
.
fluid_code
.
layers
[
0
].
param_attr
is
not
None
:
act
=
node
.
fluid_code
.
layers
[
0
].
param_attr
.
get
(
"act"
,
None
)
node
.
fluid_code
.
clear
()
attr
=
{
"dtype"
:
string
(
scale
.
dtype
),
"shape"
:
[
channel
],
"name"
:
string
(
node
.
layer_name
+
"_scale"
)
}
node
.
fluid_code
.
add_layer
(
"create_parameter"
,
inputs
=
None
,
output
=
node
.
layer_name
+
"_scale"
,
param_attr
=
attr
)
attr
=
{
"dtype"
:
string
(
scale
.
dtype
),
"shape"
:
[
channel
],
"name"
:
string
(
node
.
layer_name
+
"_bias"
)
}
node
.
fluid_code
.
add_layer
(
"create_parameter"
,
inputs
=
None
,
output
=
node
.
layer_name
+
"_bias"
,
param_attr
=
attr
)
inputs
=
{
"x"
:
in_node
,
"scale"
:
node
.
layer_name
+
"_scale"
,
"bias"
:
node
.
layer_name
+
"_bias"
}
attr
=
{
"act"
:
act
}
node
.
fluid_code
.
add_layer
(
"affine_channel"
,
inputs
=
inputs
,
output
=
node
,
param_attr
=
attr
)
del
self
.
graph
.
node_map
[
in_nodes0
[
0
].
layer_name
]
del
self
.
graph
.
node_map
[
in_nodes0
[
1
].
layer_name
]
del
self
.
graph
.
node_map
[
in_nodes1
[
1
].
layer_name
]
This diff is collapsed.
Click to expand it.
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录
新手
引导
客服
返回
顶部