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
models
提交
de4504d6
M
models
项目概览
PaddlePaddle
/
models
接近 2 年 前同步成功
通知
230
Star
6828
Fork
2962
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
602
列表
看板
标记
里程碑
合并请求
255
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
M
models
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
602
Issue
602
列表
看板
标记
里程碑
合并请求
255
合并请求
255
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
提交
de4504d6
编写于
6月 20, 2018
作者:
B
baiyfbupt
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
refine infer.py
上级
894e7ac0
变更
4
隐藏空白更改
内联
并排
Showing
4 changed file
with
320 addition
and
71 deletion
+320
-71
fluid/face_detection/.gitignore
fluid/face_detection/.gitignore
+12
-1
fluid/face_detection/infer.py
fluid/face_detection/infer.py
+257
-39
fluid/face_detection/pyramidbox.py
fluid/face_detection/pyramidbox.py
+12
-3
fluid/face_detection/reader.py
fluid/face_detection/reader.py
+39
-28
未找到文件。
fluid/face_detection/.gitignore
浏览文件 @
de4504d6
# saved model
model/
model/
# pretrained model
pretrained/
# used data and label
data/
data/
label/
label/
pretrained/
# log and swap files
*.swp
*.swp
*.log
# infer
infer_results/
fluid/face_detection/infer.py
浏览文件 @
de4504d6
...
@@ -3,6 +3,7 @@ import time
...
@@ -3,6 +3,7 @@ import time
import
numpy
as
np
import
numpy
as
np
import
argparse
import
argparse
import
functools
import
functools
import
datetime
from
PIL
import
Image
from
PIL
import
Image
from
PIL
import
ImageDraw
from
PIL
import
ImageDraw
...
@@ -11,7 +12,7 @@ import paddle.fluid as fluid
...
@@ -11,7 +12,7 @@ import paddle.fluid as fluid
import
reader
import
reader
from
pyramidbox
import
PyramidBox
from
pyramidbox
import
PyramidBox
from
utility
import
add_arguments
,
print_arguments
from
utility
import
add_arguments
,
print_arguments
from
paddle.fluid.framework
import
Program
,
Parameter
,
default_main_program
,
Variable
parser
=
argparse
.
ArgumentParser
(
description
=
__doc__
)
parser
=
argparse
.
ArgumentParser
(
description
=
__doc__
)
add_arg
=
functools
.
partial
(
add_arguments
,
argparser
=
parser
)
add_arg
=
functools
.
partial
(
add_arguments
,
argparser
=
parser
)
# yapf: disable
# yapf: disable
...
@@ -28,65 +29,282 @@ add_arg('resize_w', int, 0, "The resized image height.")
...
@@ -28,65 +29,282 @@ add_arg('resize_w', int, 0, "The resized image height.")
def
draw_bounding_box_on_image
(
image_path
,
nms_out
,
confs_threshold
):
def
draw_bounding_box_on_image
(
image_path
,
nms_out
,
confs_threshold
):
image
=
Image
.
open
(
image_path
)
image
=
Image
.
open
(
image_path
)
draw
=
ImageDraw
.
Draw
(
image
)
draw
=
ImageDraw
.
Draw
(
image
)
im_width
,
im_height
=
image
.
size
for
dt
in
nms_out
:
for
dt
in
nms_out
:
category_id
,
score
,
xmin
,
ymin
,
xmax
,
ymax
=
dt
.
tolist
()
xmin
,
ymin
,
xmax
,
ymax
,
score
=
dt
if
score
<
confs_threshold
:
if
score
<
confs_threshold
:
continue
continue
bbox
=
dt
[
2
:]
(
left
,
right
,
top
,
bottom
)
=
(
xmin
,
xmax
,
ymin
,
ymax
)
xmin
,
ymin
,
xmax
,
ymax
=
bbox
(
left
,
right
,
top
,
bottom
)
=
(
xmin
*
im_width
,
xmax
*
im_width
,
ymin
*
im_height
,
ymax
*
im_height
)
draw
.
line
(
draw
.
line
(
[(
left
,
top
),
(
left
,
bottom
),
(
right
,
bottom
),
(
right
,
top
),
[(
left
,
top
),
(
left
,
bottom
),
(
right
,
bottom
),
(
right
,
top
),
(
left
,
top
)],
(
left
,
top
)],
width
=
4
,
width
=
4
,
fill
=
'red'
)
fill
=
'red'
)
image_name
=
image_path
.
split
(
'/'
)[
-
1
]
image_name
=
image_path
.
split
(
'/'
)[
-
1
]
image_class
=
image_path
.
split
(
'/'
)[
-
2
]
print
(
"image with bbox drawed saved as {}"
.
format
(
image_name
))
print
(
"image with bbox drawed saved as {}"
.
format
(
image_name
))
image
.
save
(
image_name
)
image
.
save
(
'./infer_results/'
+
image_class
.
encode
(
'utf-8'
)
+
'/'
+
image_name
.
encode
(
'utf-8'
))
def
infer
(
args
,
data_args
):
def
write_to_txt
(
image_path
,
f
,
nms_out
):
num_classes
=
2
image_name
=
image_path
.
split
(
'/'
)[
-
1
]
infer_reader
=
reader
.
infer
(
data_args
,
args
.
image_path
)
image_class
=
image_path
.
split
(
'/'
)[
-
2
]
data
=
infer_reader
()
f
.
write
(
'{:s}
\n
'
.
format
(
image_class
.
encode
(
'utf-8'
)
+
'/'
+
image_name
.
encode
(
'utf-8'
)))
f
.
write
(
'{:d}
\n
'
.
format
(
nms_out
.
shape
[
0
]))
for
dt
in
nms_out
:
xmin
,
ymin
,
xmax
,
ymax
,
score
=
dt
f
.
write
(
'{:.1f} {:.1f} {:.1f} {:.1f} {:.3f}
\n
'
.
format
(
xmin
,
ymin
,
(
xmax
-
xmin
+
1
),
(
ymax
-
ymin
+
1
),
score
))
print
(
"image infer result saved {}"
.
format
(
image_name
[:
-
4
]))
def
get_round
(
x
,
loc
):
str_x
=
str
(
x
)
if
'.'
in
str_x
:
len_after
=
len
(
str_x
.
split
(
'.'
)[
1
])
str_before
=
str_x
.
split
(
'.'
)[
0
]
str_after
=
str_x
.
split
(
'.'
)[
1
]
if
len_after
>=
3
:
str_final
=
str_before
+
'.'
+
str_after
[
0
:
loc
]
return
float
(
str_final
)
else
:
return
x
if
args
.
resize_h
and
args
.
resize_w
:
image_shape
=
[
3
,
args
.
resize_h
,
args
.
resize_w
]
else
:
image_shape
=
data
.
shape
[
1
:]
fetches
=
[]
def
bbox_vote
(
det
):
order
=
det
[:,
4
].
ravel
().
argsort
()[::
-
1
]
det
=
det
[
order
,
:]
if
det
.
shape
[
0
]
==
0
:
dets
=
np
.
array
([[
10
,
10
,
20
,
20
,
0.002
]])
det
=
np
.
empty
(
shape
=
[
0
,
5
])
while
det
.
shape
[
0
]
>
0
:
# IOU
area
=
(
det
[:,
2
]
-
det
[:,
0
]
+
1
)
*
(
det
[:,
3
]
-
det
[:,
1
]
+
1
)
xx1
=
np
.
maximum
(
det
[
0
,
0
],
det
[:,
0
])
yy1
=
np
.
maximum
(
det
[
0
,
1
],
det
[:,
1
])
xx2
=
np
.
minimum
(
det
[
0
,
2
],
det
[:,
2
])
yy2
=
np
.
minimum
(
det
[
0
,
3
],
det
[:,
3
])
w
=
np
.
maximum
(
0.0
,
xx2
-
xx1
+
1
)
h
=
np
.
maximum
(
0.0
,
yy2
-
yy1
+
1
)
inter
=
w
*
h
o
=
inter
/
(
area
[
0
]
+
area
[:]
-
inter
)
# get needed merge det and delete these det
merge_index
=
np
.
where
(
o
>=
0.3
)[
0
]
det_accu
=
det
[
merge_index
,
:]
det
=
np
.
delete
(
det
,
merge_index
,
0
)
if
merge_index
.
shape
[
0
]
<=
1
:
if
det
.
shape
[
0
]
==
0
:
try
:
dets
=
np
.
row_stack
((
dets
,
det_accu
))
except
:
dets
=
det_accu
continue
det_accu
[:,
0
:
4
]
=
det_accu
[:,
0
:
4
]
*
np
.
tile
(
det_accu
[:,
-
1
:],
(
1
,
4
))
max_score
=
np
.
max
(
det_accu
[:,
4
])
det_accu_sum
=
np
.
zeros
((
1
,
5
))
det_accu_sum
[:,
0
:
4
]
=
np
.
sum
(
det_accu
[:,
0
:
4
],
axis
=
0
)
/
np
.
sum
(
det_accu
[:,
-
1
:])
det_accu_sum
[:,
4
]
=
max_score
try
:
dets
=
np
.
row_stack
((
dets
,
det_accu_sum
))
except
:
dets
=
det_accu_sum
dets
=
dets
[
0
:
750
,
:]
return
dets
network
=
PyramidBox
(
image_shape
,
num_classes
,
sub_network
=
args
.
use_pyramidbox
,
is_infer
=
True
)
infer_program
,
nmsed_out
=
network
.
infer
()
fetches
=
[
nmsed_out
]
def
detect_face
(
image
,
image_shape
,
raw_image
,
shrink
):
num_classes
=
2
place
=
fluid
.
CUDAPlace
(
0
)
if
args
.
use_gpu
else
fluid
.
CPUPlace
()
place
=
fluid
.
CUDAPlace
(
0
)
if
args
.
use_gpu
else
fluid
.
CPUPlace
()
exe
=
fluid
.
Executor
(
place
)
exe
=
fluid
.
Executor
(
place
)
model_dir
=
args
.
model_dir
if
shrink
!=
1
:
if
not
os
.
path
.
exists
(
model_dir
):
image
=
image
.
resize
((
int
(
image_shape
[
2
]
*
shrink
),
raise
ValueError
(
"The model path [%s] does not exist."
%
(
model_dir
))
int
(
image_shape
[
1
]
*
shrink
)),
Image
.
ANTIALIAS
)
image_shape
=
[
image_shape
[
0
],
int
(
image_shape
[
1
]
*
shrink
),
int
(
image_shape
[
2
]
*
shrink
)
]
print
"image_shape:"
,
image_shape
img
=
np
.
array
(
image
)
# HWC to CHW
if
len
(
img
.
shape
)
==
3
:
img
=
np
.
swapaxes
(
img
,
1
,
2
)
img
=
np
.
swapaxes
(
img
,
1
,
0
)
# RBG to BGR
img
=
img
[[
2
,
1
,
0
],
:,
:]
img
=
img
.
astype
(
'float32'
)
img
-=
np
.
array
(
[
104.
,
117.
,
123.
])[:,
np
.
newaxis
,
np
.
newaxis
].
astype
(
'float32'
)
img
=
img
*
0.007843
img
=
[
img
]
img
=
np
.
array
(
img
)
scope
=
fluid
.
core
.
Scope
()
model_program
=
fluid
.
Program
()
startup_program
=
fluid
.
Program
()
with
fluid
.
scope_guard
(
scope
):
with
fluid
.
unique_name
.
guard
():
with
fluid
.
program_guard
(
model_program
,
startup_program
):
fetches
=
[]
network
=
PyramidBox
(
image_shape
,
num_classes
,
sub_network
=
args
.
use_pyramidbox
,
is_infer
=
True
)
infer_program
,
nmsed_out
=
network
.
infer
()
fetches
=
[
nmsed_out
]
feeder
=
fluid
.
DataFeeder
(
place
=
place
,
feed_list
=
network
.
feeds
())
fluid
.
io
.
load_persistables
(
exe
,
args
.
model_dir
,
main_program
=
model_program
)
#fluid.io.load_vars(exe, args.model_dir, predicate=if_exist)
detection
,
=
exe
.
run
(
infer_program
,
feed
=
feeder
.
feed
([
img
]),
fetch_list
=
fetches
,
return_numpy
=
False
)
detection
=
np
.
array
(
detection
)
# layout: xmin, ymin, xmax. ymax, score
det_conf
=
detection
[:,
1
]
if
args
.
resize_h
!=
0
and
args
.
resize_w
!=
0
:
det_xmin
=
raw_image
.
size
[
0
]
*
detection
[:,
2
]
det_ymin
=
raw_image
.
size
[
1
]
*
detection
[:,
3
]
det_xmax
=
raw_image
.
size
[
0
]
*
detection
[:,
4
]
det_ymax
=
raw_image
.
size
[
1
]
*
detection
[:,
5
]
else
:
det_xmin
=
image_shape
[
2
]
*
detection
[:,
2
]
/
shrink
det_ymin
=
image_shape
[
1
]
*
detection
[:,
3
]
/
shrink
det_xmax
=
image_shape
[
2
]
*
detection
[:,
4
]
/
shrink
det_ymax
=
image_shape
[
1
]
*
detection
[:,
5
]
/
shrink
det
=
np
.
column_stack
((
det_xmin
,
det_ymin
,
det_xmax
,
det_ymax
,
det_conf
))
keep_index
=
np
.
where
(
det
[:,
4
]
>=
0
)[
0
]
det
=
det
[
keep_index
,
:]
return
det
def
flip_test
(
image
,
image_shape
,
raw_image
,
shrink
):
image
=
image
.
transpose
(
Image
.
FLIP_LEFT_RIGHT
)
det_f
=
detect_face
(
image
,
image_shape
,
raw_image
,
shrink
)
det_t
=
np
.
zeros
(
det_f
.
shape
)
det_t
[:,
0
]
=
raw_image
.
size
[
0
]
-
det_f
[:,
2
]
det_t
[:,
1
]
=
det_f
[:,
1
]
det_t
[:,
2
]
=
raw_image
.
size
[
0
]
-
det_f
[:,
0
]
det_t
[:,
3
]
=
det_f
[:,
3
]
det_t
[:,
4
]
=
det_f
[:,
4
]
return
det_t
def
multi_scale_test
(
image
,
image_shape
,
raw_image
,
max_im_shrink
):
# shrink detecting and shrink only detect big face
st
=
0.5
if
max_im_shrink
>=
0.75
else
0.5
*
max_im_shrink
det_s
=
detect_face
(
image
,
image_shape
,
raw_image
,
st
)
index
=
np
.
where
(
np
.
maximum
(
det_s
[:,
2
]
-
det_s
[:,
0
]
+
1
,
det_s
[:,
3
]
-
det_s
[:,
1
]
+
1
)
>
30
)[
0
]
det_s
=
det_s
[
index
,
:]
# enlarge one times
bt
=
min
(
2
,
max_im_shrink
)
if
max_im_shrink
>
1
else
(
st
+
max_im_shrink
)
/
2
det_b
=
detect_face
(
image
,
image_shape
,
raw_image
,
bt
)
# enlarge small iamge x times for small face
if
max_im_shrink
>
2
:
bt
*=
2
while
bt
<
max_im_shrink
:
det_b
=
np
.
row_stack
(
(
det_b
,
detect_face
(
image
,
image_shape
,
raw_image
,
bt
)))
bt
*=
2
det_b
=
np
.
row_stack
(
(
det_b
,
detect_face
(
image
,
image_shape
,
raw_image
,
max_im_shrink
)))
# enlarge only detect small face
if
bt
>
1
:
index
=
np
.
where
(
np
.
minimum
(
det_b
[:,
2
]
-
det_b
[:,
0
]
+
1
,
det_b
[:,
3
]
-
det_b
[:,
1
]
+
1
)
<
100
)[
0
]
det_b
=
det_b
[
index
,
:]
else
:
index
=
np
.
where
(
np
.
maximum
(
det_b
[:,
2
]
-
det_b
[:,
0
]
+
1
,
det_b
[:,
3
]
-
det_b
[:,
1
]
+
1
)
>
30
)[
0
]
det_b
=
det_b
[
index
,
:]
return
det_s
,
det_b
def
get_im_shrink
(
image_shape
):
max_im_shrink_v1
=
(
0x7fffffff
/
577.0
/
(
image_shape
[
1
]
*
image_shape
[
2
]))
**
0.5
max_im_shrink_v2
=
(
(
678
*
1024
*
2.0
*
2.0
)
/
(
image_shape
[
1
]
*
image_shape
[
2
]))
**
0.5
max_im_shrink
=
get_round
(
min
(
max_im_shrink_v1
,
max_im_shrink_v2
),
2
)
-
0.3
if
max_im_shrink
>=
1.5
and
max_im_shrink
<
2
:
max_im_shrink
=
max_im_shrink
-
0.1
elif
max_im_shrink
>=
2
and
max_im_shrink
<
3
:
max_im_shrink
=
max_im_shrink
-
0.2
elif
max_im_shrink
>=
3
and
max_im_shrink
<
4
:
max_im_shrink
=
max_im_shrink
-
0.3
elif
max_im_shrink
>=
4
and
max_im_shrink
<
5
:
max_im_shrink
=
max_im_shrink
-
0.4
elif
max_im_shrink
>=
5
and
max_im_shrink
<
6
:
max_im_shrink
=
max_im_shrink
-
0.5
elif
max_im_shrink
>=
6
:
max_im_shrink
=
max_im_shrink
-
0.5
print
'max_im_shrink = '
,
max_im_shrink
shrink
=
max_im_shrink
if
max_im_shrink
<
1
else
1
print
"shrink = "
,
shrink
return
shrink
,
max_im_shrink
def
infer
(
args
,
batch_size
,
data_args
):
if
not
os
.
path
.
exists
(
args
.
model_dir
):
raise
ValueError
(
"The model path [%s] does not exist."
%
(
args
.
model_dir
))
infer_reader
=
paddle
.
batch
(
reader
.
test
(
data_args
,
file_list
),
batch_size
=
batch_size
)
for
batch_id
,
img
in
enumerate
(
infer_reader
()):
image
=
img
[
0
][
0
]
image_path
=
img
[
0
][
1
]
raw_image
=
Image
.
open
(
image_path
)
if
args
.
resize_h
!=
0
and
args
.
resize_w
!=
0
:
image_shape
=
[
3
,
args
.
resize_h
,
args
.
resize_w
]
else
:
image_shape
=
[
3
,
image
.
size
[
1
],
image
.
size
[
0
]]
shrink
,
max_im_shrink
=
get_im_shrink
(
image_shape
)
det0
=
detect_face
(
image
,
image_shape
,
raw_image
,
shrink
)
det1
=
flip_test
(
image
,
image_shape
,
raw_image
,
shrink
)
[
det2
,
det3
]
=
multi_scale_test
(
image
,
image_shape
,
raw_image
,
max_im_shrink
)
det
=
np
.
row_stack
((
det0
,
det1
,
det2
,
det3
))
dets
=
bbox_vote
(
det
)
def
if_exist
(
var
):
image_name
=
image_path
.
split
(
'/'
)[
-
1
]
return
os
.
path
.
exists
(
os
.
path
.
join
(
model_dir
,
var
.
name
))
image_class
=
image_path
.
split
(
'/'
)[
-
2
]
fluid
.
io
.
load_vars
(
exe
,
model_dir
,
predicate
=
if_exist
)
if
not
os
.
path
.
exists
(
'./infer_results/'
+
image_class
.
encode
(
'utf-8'
)):
os
.
makedirs
(
'./infer_results/'
+
image_class
.
encode
(
'utf-8'
))
feed
=
{
'image'
:
fluid
.
create_lod_tensor
(
data
,
[],
place
)}
f
=
open
(
'./infer_results/'
+
image_class
.
encode
(
'utf-8'
)
+
'/'
+
predict
,
=
exe
.
run
(
infer_program
,
image_name
.
encode
(
'utf-8'
)[:
-
4
]
+
'.txt'
,
'w'
)
feed
=
feed
,
write_to_txt
(
image_path
,
f
,
dets
)
fetch_list
=
fetches
,
#draw_bounding_box_on_image(image_path, dets, args.confs_threshold)
return_numpy
=
False
)
print
"Done"
predict
=
np
.
array
(
predict
)
draw_bounding_box_on_image
(
args
.
image_path
,
predict
,
args
.
confs_threshold
)
if
__name__
==
'__main__'
:
if
__name__
==
'__main__'
:
...
@@ -104,4 +322,4 @@ if __name__ == '__main__':
...
@@ -104,4 +322,4 @@ if __name__ == '__main__':
apply_distort
=
False
,
apply_distort
=
False
,
apply_expand
=
False
,
apply_expand
=
False
,
ap_version
=
'11point'
)
ap_version
=
'11point'
)
infer
(
args
,
data_args
=
data_args
)
infer
(
args
,
batch_size
=
1
,
data_args
=
data_args
)
fluid/face_detection/pyramidbox.py
浏览文件 @
de4504d6
...
@@ -39,7 +39,11 @@ def conv_block(input, groups, filters, ksizes, strides=None, with_pool=True):
...
@@ -39,7 +39,11 @@ def conv_block(input, groups, filters, ksizes, strides=None, with_pool=True):
act
=
'relu'
)
act
=
'relu'
)
if
with_pool
:
if
with_pool
:
pool
=
fluid
.
layers
.
pool2d
(
pool
=
fluid
.
layers
.
pool2d
(
input
=
conv
,
pool_size
=
2
,
pool_type
=
'max'
,
pool_stride
=
2
)
input
=
conv
,
pool_size
=
2
,
pool_type
=
'max'
,
pool_stride
=
2
,
ceil_mode
=
True
)
return
conv
,
pool
return
conv
,
pool
else
:
else
:
return
conv
return
conv
...
@@ -148,6 +152,8 @@ class PyramidBox(object):
...
@@ -148,6 +152,8 @@ class PyramidBox(object):
b_attr
=
ParamAttr
(
learning_rate
=
2.
,
regularizer
=
L2Decay
(
0.
))
b_attr
=
ParamAttr
(
learning_rate
=
2.
,
regularizer
=
L2Decay
(
0.
))
conv2
=
fluid
.
layers
.
conv2d
(
conv2
=
fluid
.
layers
.
conv2d
(
up_to
,
ch
,
1
,
act
=
'relu'
,
bias_attr
=
b_attr
)
up_to
,
ch
,
1
,
act
=
'relu'
,
bias_attr
=
b_attr
)
if
self
.
is_infer
:
upsampling
=
fluid
.
layers
.
crop
(
upsampling
,
shape
=
conv2
)
# eltwise mul
# eltwise mul
conv_fuse
=
upsampling
*
conv2
conv_fuse
=
upsampling
*
conv2
return
conv_fuse
return
conv_fuse
...
@@ -393,8 +399,11 @@ class PyramidBox(object):
...
@@ -393,8 +399,11 @@ class PyramidBox(object):
total_loss
=
face_loss
+
head_loss
total_loss
=
face_loss
+
head_loss
return
face_loss
,
head_loss
,
total_loss
return
face_loss
,
head_loss
,
total_loss
def
infer
(
self
):
def
infer
(
self
,
main_program
=
None
):
test_program
=
fluid
.
default_main_program
().
clone
(
for_test
=
True
)
if
main_program
is
None
:
test_program
=
fluid
.
default_main_program
().
clone
(
for_test
=
True
)
else
:
test_program
=
main_program
.
clone
(
for_test
=
True
)
with
fluid
.
program_guard
(
test_program
):
with
fluid
.
program_guard
(
test_program
):
face_nmsed_out
=
fluid
.
layers
.
detection_output
(
face_nmsed_out
=
fluid
.
layers
.
detection_output
(
self
.
face_mbox_loc
,
self
.
face_mbox_loc
,
...
...
fluid/face_detection/reader.py
浏览文件 @
de4504d6
...
@@ -238,34 +238,41 @@ def pyramidbox(settings, file_list, mode, shuffle):
...
@@ -238,34 +238,41 @@ def pyramidbox(settings, file_list, mode, shuffle):
im_width
,
im_height
=
im
.
size
im_width
,
im_height
=
im
.
size
# layout: label | xmin | ymin | xmax | ymax
# layout: label | xmin | ymin | xmax | ymax
bbox_labels
=
[]
if
mode
==
'train'
:
for
index_box
in
range
(
len
(
dict_input_txt
[
index_image
])):
bbox_labels
=
[]
if
index_box
>=
2
:
for
index_box
in
range
(
len
(
dict_input_txt
[
index_image
])):
bbox_sample
=
[]
if
index_box
>=
2
:
temp_info_box
=
dict_input_txt
[
index_image
][
bbox_sample
=
[]
index_box
].
split
(
' '
)
temp_info_box
=
dict_input_txt
[
index_image
][
xmin
=
float
(
temp_info_box
[
0
])
index_box
].
split
(
' '
)
ymin
=
float
(
temp_info_box
[
1
])
xmin
=
float
(
temp_info_box
[
0
])
w
=
float
(
temp_info_box
[
2
])
ymin
=
float
(
temp_info_box
[
1
])
h
=
float
(
temp_info_box
[
3
])
w
=
float
(
temp_info_box
[
2
])
xmax
=
xmin
+
w
h
=
float
(
temp_info_box
[
3
])
ymax
=
ymin
+
h
xmax
=
xmin
+
w
ymax
=
ymin
+
h
bbox_sample
.
append
(
1
)
bbox_sample
.
append
(
float
(
xmin
)
/
im_width
)
bbox_sample
.
append
(
1
)
bbox_sample
.
append
(
float
(
ymin
)
/
im_height
)
bbox_sample
.
append
(
float
(
xmin
)
/
im_width
)
bbox_sample
.
append
(
float
(
xmax
)
/
im_width
)
bbox_sample
.
append
(
float
(
ymin
)
/
im_height
)
bbox_sample
.
append
(
float
(
ymax
)
/
im_height
)
bbox_sample
.
append
(
float
(
xmax
)
/
im_width
)
bbox_labels
.
append
(
bbox_sample
)
bbox_sample
.
append
(
float
(
ymax
)
/
im_height
)
bbox_labels
.
append
(
bbox_sample
)
im
,
sample_labels
=
preprocess
(
im
,
bbox_labels
,
mode
,
settings
)
sample_labels
=
np
.
array
(
sample_labels
)
im
,
sample_labels
=
preprocess
(
im
,
bbox_labels
,
mode
,
settings
)
if
len
(
sample_labels
)
==
0
:
continue
sample_labels
=
np
.
array
(
sample_labels
)
im
=
im
.
astype
(
'float32'
)
if
len
(
sample_labels
)
==
0
:
continue
boxes
=
sample_labels
[:,
1
:
5
]
im
=
im
.
astype
(
'float32'
)
lbls
=
[
1
]
*
len
(
boxes
)
boxes
=
sample_labels
[:,
1
:
5
]
difficults
=
[
1
]
*
len
(
boxes
)
lbls
=
[
1
]
*
len
(
boxes
)
yield
im
,
boxes
,
expand_bboxes
(
boxes
),
lbls
,
difficults
difficults
=
[
1
]
*
len
(
boxes
)
yield
im
,
boxes
,
expand_bboxes
(
boxes
),
lbls
,
difficults
if
mode
==
'test'
:
if
settings
.
resize_w
and
settings
.
resize_h
:
im
=
im
.
resize
((
settings
.
resize_w
,
settings
.
resize_h
),
Image
.
ANTIALIAS
)
yield
im
,
image_path
return
reader
return
reader
...
@@ -274,6 +281,10 @@ def train(settings, file_list, shuffle=True):
...
@@ -274,6 +281,10 @@ def train(settings, file_list, shuffle=True):
return
pyramidbox
(
settings
,
file_list
,
'train'
,
shuffle
)
return
pyramidbox
(
settings
,
file_list
,
'train'
,
shuffle
)
def
test
(
settings
,
file_list
):
return
pyramidbox
(
settings
,
file_list
,
'test'
,
False
)
def
infer
(
settings
,
image_path
):
def
infer
(
settings
,
image_path
):
def
batch_reader
():
def
batch_reader
():
img
=
Image
.
open
(
image_path
)
img
=
Image
.
open
(
image_path
)
...
...
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