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
PaddleDetection
提交
d40d28d8
P
PaddleDetection
项目概览
PaddlePaddle
/
PaddleDetection
大约 1 年 前同步成功
通知
694
Star
11112
Fork
2696
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
184
列表
看板
标记
里程碑
合并请求
40
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
PaddleDetection
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
184
Issue
184
列表
看板
标记
里程碑
合并请求
40
合并请求
40
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
体验新版 GitCode,发现更多精彩内容 >>
未验证
提交
d40d28d8
编写于
12月 15, 2017
作者:
G
Guo Sheng
提交者:
GitHub
12月 15, 2017
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #6515 from guoshengCS/add-multiBatch-chunkEval
Add ChunkEvaluator for Multi-batches
上级
78c20e3e
a7fa2051
变更
6
隐藏空白更改
内联
并排
Showing
6 changed file
with
151 addition
and
31 deletion
+151
-31
paddle/operators/chunk_eval_op.cc
paddle/operators/chunk_eval_op.cc
+20
-0
paddle/operators/chunk_eval_op.h
paddle/operators/chunk_eval_op.h
+29
-13
python/paddle/v2/fluid/evaluator.py
python/paddle/v2/fluid/evaluator.py
+72
-1
python/paddle/v2/fluid/layers/nn.py
python/paddle/v2/fluid/layers/nn.py
+10
-4
python/paddle/v2/fluid/tests/book/test_label_semantic_roles.py
...n/paddle/v2/fluid/tests/book/test_label_semantic_roles.py
+13
-12
python/paddle/v2/fluid/tests/test_chunk_eval_op.py
python/paddle/v2/fluid/tests/test_chunk_eval_op.py
+7
-1
未找到文件。
paddle/operators/chunk_eval_op.cc
浏览文件 @
d40d28d8
...
...
@@ -32,6 +32,13 @@ class ChunkEvalOp : public framework::OperatorWithKernel {
"Output(Recall) of ChunkEvalOp should not be null."
);
PADDLE_ENFORCE
(
ctx
->
HasOutput
(
"F1-Score"
),
"Output(F1-Score) of ChunkEvalOp should not be null."
);
PADDLE_ENFORCE
(
ctx
->
HasOutput
(
"NumInferChunks"
),
"Output(NumInferChunks) of ChunkEvalOp should not be null."
);
PADDLE_ENFORCE
(
ctx
->
HasOutput
(
"NumLabelChunks"
),
"Output(NumLabelChunks) of ChunkEvalOp should not be null."
);
PADDLE_ENFORCE
(
ctx
->
HasOutput
(
"NumCorrectChunks"
),
"Output(NumCorrectChunks) of ChunkEvalOp should not be null."
);
auto
inference_dim
=
ctx
->
GetInputDim
(
"Inference"
);
auto
label_dim
=
ctx
->
GetInputDim
(
"Label"
);
...
...
@@ -42,6 +49,9 @@ class ChunkEvalOp : public framework::OperatorWithKernel {
ctx
->
SetOutputDim
(
"Precision"
,
{
1
});
ctx
->
SetOutputDim
(
"Recall"
,
{
1
});
ctx
->
SetOutputDim
(
"F1-Score"
,
{
1
});
ctx
->
SetOutputDim
(
"NumInferChunks"
,
{
1
});
ctx
->
SetOutputDim
(
"NumLabelChunks"
,
{
1
});
ctx
->
SetOutputDim
(
"NumCorrectChunks"
,
{
1
});
}
protected:
...
...
@@ -70,6 +80,16 @@ class ChunkEvalOpMaker : public framework::OpProtoAndCheckerMaker {
"sensitivity) of chunks on the given mini-batch."
);
AddOutput
(
"F1-Score"
,
"(float). The evaluated F1-Score on the given mini-batch."
);
AddOutput
(
"NumInferChunks"
,
"(int64_t). The number of chunks in Inference on the given "
"mini-batch."
);
AddOutput
(
"NumLabelChunks"
,
"(int64_t). The number of chunks in Label on the given mini-batch."
);
AddOutput
(
"NumCorrectChunks"
,
"(int64_t). The number of chunks both in Inference and Label on the "
"given mini-batch."
);
AddAttr
<
int
>
(
"num_chunk_types"
,
"(int). The number of chunk type. See below for details."
);
AddAttr
<
std
::
string
>
(
...
...
paddle/operators/chunk_eval_op.h
浏览文件 @
d40d28d8
...
...
@@ -111,9 +111,7 @@ class ChunkEvalKernel : public framework::OpKernel<T> {
std
::
vector
<
Segment
>
label_segments
;
std
::
vector
<
Segment
>
output_segments
;
std
::
set
<
int
>
excluded_chunk_types
;
int64_t
num_output_segments
=
0
;
int64_t
num_label_segments
=
0
;
int64_t
num_correct
=
0
;
if
(
context
.
Attr
<
std
::
string
>
(
"chunk_scheme"
)
==
"IOB"
)
{
num_tag_types
=
2
;
tag_begin
=
0
;
...
...
@@ -151,12 +149,24 @@ class ChunkEvalKernel : public framework::OpKernel<T> {
auto
*
precision
=
context
.
Output
<
Tensor
>
(
"Precision"
);
auto
*
recall
=
context
.
Output
<
Tensor
>
(
"Recall"
);
auto
*
f1
=
context
.
Output
<
Tensor
>
(
"F1-Score"
);
auto
*
num_infer_chunks
=
context
.
Output
<
Tensor
>
(
"NumInferChunks"
);
auto
*
num_label_chunks
=
context
.
Output
<
Tensor
>
(
"NumLabelChunks"
);
auto
*
num_correct_chunks
=
context
.
Output
<
Tensor
>
(
"NumCorrectChunks"
);
const
int64_t
*
inference_data
=
inference
->
data
<
int64_t
>
();
const
int64_t
*
label_data
=
label
->
data
<
int64_t
>
();
T
*
precision_data
=
precision
->
mutable_data
<
T
>
(
context
.
GetPlace
());
T
*
racall_data
=
recall
->
mutable_data
<
T
>
(
context
.
GetPlace
());
T
*
f1_data
=
f1
->
mutable_data
<
T
>
(
context
.
GetPlace
());
int64_t
*
num_infer_chunks_data
=
num_infer_chunks
->
mutable_data
<
int64_t
>
(
context
.
GetPlace
());
int64_t
*
num_label_chunks_data
=
num_label_chunks
->
mutable_data
<
int64_t
>
(
context
.
GetPlace
());
int64_t
*
num_correct_chunks_data
=
num_correct_chunks
->
mutable_data
<
int64_t
>
(
context
.
GetPlace
());
*
num_infer_chunks_data
=
0
;
*
num_label_chunks_data
=
0
;
*
num_correct_chunks_data
=
0
;
auto
lod
=
label
->
lod
();
PADDLE_ENFORCE_EQ
(
lod
.
size
(),
1UL
,
"Only support one level sequence now."
);
...
...
@@ -166,17 +176,23 @@ class ChunkEvalKernel : public framework::OpKernel<T> {
for
(
int
i
=
0
;
i
<
num_sequences
;
++
i
)
{
int
seq_length
=
lod
[
0
][
i
+
1
]
-
lod
[
0
][
i
];
EvalOneSeq
(
inference_data
+
lod
[
0
][
i
],
label_data
+
lod
[
0
][
i
],
seq_length
,
output_segments
,
label_segments
,
num_output_segments
,
num_label_segments
,
num_correct
,
num_chunk_types
,
num_
tag_types
,
other_chunk_type
,
tag_begin
,
tag_inside
,
tag_end
,
tag_single
,
excluded_chunk_types
);
output_segments
,
label_segments
,
*
num_infer_chunks_data
,
*
num_label_chunks_data
,
*
num_correct_chunks_data
,
num_
chunk_types
,
num_tag_types
,
other_chunk_type
,
tag_begin
,
tag_
inside
,
tag_
end
,
tag_single
,
excluded_chunk_types
);
}
*
precision_data
=
!
num_output_segments
?
0
:
static_cast
<
T
>
(
num_correct
)
/
num_output_segments
;
*
racall_data
=
!
num_label_segments
?
0
:
static_cast
<
T
>
(
num_correct
)
/
num_label_segments
;
*
f1_data
=
!
num_correct
?
0
:
2
*
(
*
precision_data
)
*
(
*
racall_data
)
/
((
*
precision_data
)
+
(
*
racall_data
));
*
precision_data
=
!
(
*
num_infer_chunks_data
)
?
0
:
static_cast
<
T
>
(
*
num_correct_chunks_data
)
/
(
*
num_infer_chunks_data
);
*
racall_data
=
!
(
*
num_label_chunks_data
)
?
0
:
static_cast
<
T
>
(
*
num_correct_chunks_data
)
/
(
*
num_label_chunks_data
);
*
f1_data
=
!
(
*
num_correct_chunks_data
)
?
0
:
2
*
(
*
precision_data
)
*
(
*
racall_data
)
/
((
*
precision_data
)
+
(
*
racall_data
));
}
void
EvalOneSeq
(
const
int64_t
*
output
,
const
int64_t
*
label
,
int
length
,
...
...
python/paddle/v2/fluid/evaluator.py
浏览文件 @
d40d28d8
...
...
@@ -4,7 +4,7 @@ import layers
from
framework
import
Program
,
unique_name
,
Variable
from
layer_helper
import
LayerHelper
__all__
=
[
'Accuracy'
]
__all__
=
[
'Accuracy'
,
'ChunkEvaluator'
]
def
_clone_var_
(
block
,
var
):
...
...
@@ -132,3 +132,74 @@ class Accuracy(Evaluator):
correct
=
layers
.
cast
(
correct
,
dtype
=
'float32'
,
**
kwargs
)
out
=
layers
.
elementwise_div
(
x
=
correct
,
y
=
total
,
**
kwargs
)
return
np
.
array
(
executor
.
run
(
eval_program
,
fetch_list
=
[
out
])[
0
])
class
ChunkEvaluator
(
Evaluator
):
"""
Accumulate counter numbers output by chunk_eval from mini-batches and
compute the precision recall and F1-score using the accumulated counter
numbers.
"""
def
__init__
(
self
,
input
,
label
,
chunk_scheme
,
num_chunk_types
,
excluded_chunk_types
=
None
,
**
kwargs
):
super
(
ChunkEvaluator
,
self
).
__init__
(
"chunk_eval"
,
**
kwargs
)
main_program
=
self
.
helper
.
main_program
if
main_program
.
current_block
().
idx
!=
0
:
raise
ValueError
(
"You can only invoke Evaluator in root block"
)
self
.
num_infer_chunks
=
self
.
create_state
(
dtype
=
'int64'
,
shape
=
[
1
],
suffix
=
'num_infer_chunks'
)
self
.
num_label_chunks
=
self
.
create_state
(
dtype
=
'int64'
,
shape
=
[
1
],
suffix
=
'num_label_chunks'
)
self
.
num_correct_chunks
=
self
.
create_state
(
dtype
=
'int64'
,
shape
=
[
1
],
suffix
=
'num_correct_chunks'
)
kwargs
=
{
'main_program'
:
main_program
}
precision
,
recall
,
f1_score
,
num_infer_chunks
,
num_label_chunks
,
num_correct_chunks
=
layers
.
chunk_eval
(
input
=
input
,
label
=
label
,
chunk_scheme
=
chunk_scheme
,
num_chunk_types
=
num_chunk_types
,
excluded_chunk_types
=
excluded_chunk_types
,
**
kwargs
)
layers
.
sums
(
input
=
[
self
.
num_infer_chunks
,
num_infer_chunks
],
out
=
self
.
num_infer_chunks
,
**
kwargs
)
layers
.
sums
(
input
=
[
self
.
num_label_chunks
,
num_label_chunks
],
out
=
self
.
num_label_chunks
,
**
kwargs
)
layers
.
sums
(
input
=
[
self
.
num_correct_chunks
,
num_correct_chunks
],
out
=
self
.
num_correct_chunks
,
**
kwargs
)
self
.
metrics
.
extend
([
precision
,
recall
,
f1_score
])
def
eval
(
self
,
executor
,
eval_program
=
None
):
if
eval_program
is
None
:
eval_program
=
Program
()
block
=
eval_program
.
current_block
()
kwargs
=
{
'main_program'
:
eval_program
}
num_infer_chunks
,
num_label_chunks
,
num_correct_chunks
=
executor
.
run
(
eval_program
,
fetch_list
=
[
_clone_var_
(
block
,
state
)
for
state
in
self
.
states
])
num_infer_chunks
=
num_infer_chunks
[
0
]
num_label_chunks
=
num_label_chunks
[
0
]
num_correct_chunks
=
num_correct_chunks
[
0
]
precision
=
float
(
num_correct_chunks
)
/
num_infer_chunks
if
num_infer_chunks
else
0
recall
=
float
(
num_correct_chunks
)
/
num_label_chunks
if
num_label_chunks
else
0
f1_score
=
float
(
2
*
precision
*
recall
)
/
(
precision
+
recall
)
if
num_correct_chunks
else
0
return
np
.
array
(
[
precision
],
dtype
=
'float32'
),
np
.
array
(
[
recall
],
dtype
=
'float32'
),
np
.
array
(
[
f1_score
],
dtype
=
'float32'
)
python/paddle/v2/fluid/layers/nn.py
浏览文件 @
d40d28d8
...
...
@@ -392,8 +392,8 @@ def chunk_eval(input,
excluded_chunk_types
=
None
,
**
kwargs
):
"""
This function computes
the accuracy using the input and label.
The output is the top_k inputs and their indices
.
This function computes
and outputs the precision, recall and
F1-score of chunk detection
.
"""
helper
=
LayerHelper
(
"chunk_eval"
,
**
kwargs
)
...
...
@@ -401,6 +401,9 @@ def chunk_eval(input,
precision
=
helper
.
create_tmp_variable
(
dtype
=
"float32"
)
recall
=
helper
.
create_tmp_variable
(
dtype
=
"float32"
)
f1_score
=
helper
.
create_tmp_variable
(
dtype
=
"float32"
)
num_infer_chunks
=
helper
.
create_tmp_variable
(
dtype
=
"int64"
)
num_label_chunks
=
helper
.
create_tmp_variable
(
dtype
=
"int64"
)
num_correct_chunks
=
helper
.
create_tmp_variable
(
dtype
=
"int64"
)
helper
.
append_op
(
type
=
"chunk_eval"
,
...
...
@@ -409,14 +412,17 @@ def chunk_eval(input,
outputs
=
{
"Precision"
:
[
precision
],
"Recall"
:
[
recall
],
"F1-Score"
:
[
f1_score
]
"F1-Score"
:
[
f1_score
],
"NumInferChunks"
:
[
num_infer_chunks
],
"NumLabelChunks"
:
[
num_label_chunks
],
"NumCorrectChunks"
:
[
num_correct_chunks
]
},
attrs
=
{
"num_chunk_types"
:
num_chunk_types
,
'chunk_scheme'
:
chunk_scheme
,
'excluded_chunk_types'
:
excluded_chunk_types
or
[]
})
return
precision
,
recall
,
f1_score
return
precision
,
recall
,
f1_score
,
num_infer_chunks
,
num_label_chunks
,
num_correct_chunks
def
sequence_conv
(
input
,
...
...
python/paddle/v2/fluid/tests/book/test_label_semantic_roles.py
浏览文件 @
d40d28d8
...
...
@@ -150,7 +150,7 @@ def main():
crf_decode
=
fluid
.
layers
.
crf_decoding
(
input
=
feature_out
,
param_attr
=
fluid
.
ParamAttr
(
name
=
'crfw'
))
precision
,
recall
,
f1_score
=
fluid
.
layers
.
chunk_eval
(
chunk_evaluator
=
fluid
.
evaluator
.
ChunkEvaluator
(
input
=
crf_decode
,
label
=
target
,
chunk_scheme
=
"IOB"
,
...
...
@@ -176,20 +176,21 @@ def main():
batch_id
=
0
for
pass_id
in
xrange
(
PASS_NUM
):
chunk_evaluator
.
reset
(
exe
)
for
data
in
train_data
():
outs
=
exe
.
run
(
fluid
.
default_main_program
(),
feed
=
feeder
.
feed
(
data
),
fetch_list
=
[
avg_cost
,
precision
,
recall
,
f1_score
])
avg_cost_val
=
np
.
array
(
outs
[
0
])
precision_val
=
np
.
array
(
outs
[
1
])
recall_val
=
np
.
array
(
outs
[
2
])
f1_score_val
=
np
.
array
(
outs
[
3
])
cost
,
precision
,
recall
,
f1_score
=
exe
.
run
(
fluid
.
default_main_program
(),
feed
=
feeder
.
feed
(
data
),
fetch_list
=
[
avg_cost
]
+
chunk_evaluator
.
metrics
)
pass_precision
,
pass_recall
,
pass_f1_score
=
chunk_evaluator
.
eval
(
exe
)
if
batch_id
%
10
==
0
:
print
(
"avg_cost="
+
str
(
avg_cost_val
))
print
(
"precision_val="
+
str
(
precision_val
))
print
(
"recall_val:"
+
str
(
recall_val
))
print
(
"f1_score_val:"
+
str
(
f1_score_val
))
print
(
"avg_cost:"
+
str
(
cost
)
+
" precision:"
+
str
(
precision
)
+
" recall:"
+
str
(
recall
)
+
" f1_score:"
+
str
(
f1_score
)
+
" pass_precision:"
+
str
(
pass_precision
)
+
" pass_recall:"
+
str
(
pass_recall
)
+
" pass_f1_score:"
+
str
(
pass_f1_score
))
# exit early for CI
exit
(
0
)
...
...
python/paddle/v2/fluid/tests/test_chunk_eval_op.py
浏览文件 @
d40d28d8
...
...
@@ -147,7 +147,13 @@ class TestChunkEvalOp(OpTest):
'Recall'
:
np
.
asarray
(
[
recall
],
dtype
=
'float32'
),
'F1-Score'
:
np
.
asarray
(
[
f1
],
dtype
=
'float32'
)
[
f1
],
dtype
=
'float32'
),
'NumInferChunks'
:
np
.
asarray
(
[
self
.
num_infer_chunks
],
dtype
=
'int64'
),
'NumLabelChunks'
:
np
.
asarray
(
[
self
.
num_label_chunks
],
dtype
=
'int64'
),
'NumCorrectChunks'
:
np
.
asarray
(
[
self
.
num_correct_chunks
],
dtype
=
'int64'
)
}
def
setUp
(
self
):
...
...
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