Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
wangsen
paddle_dbnet
Commits
07026825
Unverified
Commit
07026825
authored
Jul 19, 2021
by
zhoujun
Committed by
GitHub
Jul 19, 2021
Browse files
Merge pull request #3289 from WenmuZhou/fx_pse
fix a bug of train log not save and add filepath check to dataset
parents
4dbbfd67
f7a62d94
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
18 additions
and
14 deletions
+18
-14
ppocr/data/simple_dataset.py
ppocr/data/simple_dataset.py
+18
-11
tools/infer/utility.py
tools/infer/utility.py
+0
-3
No files found.
ppocr/data/simple_dataset.py
View file @
07026825
...
@@ -46,6 +46,7 @@ class SimpleDataSet(Dataset):
...
@@ -46,6 +46,7 @@ class SimpleDataSet(Dataset):
self
.
seed
=
seed
self
.
seed
=
seed
logger
.
info
(
"Initialize indexs of datasets:%s"
%
label_file_list
)
logger
.
info
(
"Initialize indexs of datasets:%s"
%
label_file_list
)
self
.
data_lines
=
self
.
get_image_info_list
(
label_file_list
,
ratio_list
)
self
.
data_lines
=
self
.
get_image_info_list
(
label_file_list
,
ratio_list
)
self
.
check_data
()
self
.
data_idx_order_list
=
list
(
range
(
len
(
self
.
data_lines
)))
self
.
data_idx_order_list
=
list
(
range
(
len
(
self
.
data_lines
)))
if
self
.
mode
==
"train"
and
self
.
do_shuffle
:
if
self
.
mode
==
"train"
and
self
.
do_shuffle
:
self
.
shuffle_data_random
()
self
.
shuffle_data_random
()
...
@@ -102,16 +103,8 @@ class SimpleDataSet(Dataset):
...
@@ -102,16 +103,8 @@ class SimpleDataSet(Dataset):
def
__getitem__
(
self
,
idx
):
def
__getitem__
(
self
,
idx
):
file_idx
=
self
.
data_idx_order_list
[
idx
]
file_idx
=
self
.
data_idx_order_list
[
idx
]
data
_line
=
self
.
data_lines
[
file_idx
]
data
=
self
.
data_lines
[
file_idx
]
try
:
try
:
data_line
=
data_line
.
decode
(
'utf-8'
)
substr
=
data_line
.
strip
(
"
\n
"
).
strip
(
"
\r
"
).
split
(
self
.
delimiter
)
file_name
=
substr
[
0
]
label
=
substr
[
1
]
img_path
=
os
.
path
.
join
(
self
.
data_dir
,
file_name
)
data
=
{
'img_path'
:
img_path
,
'label'
:
label
}
if
not
os
.
path
.
exists
(
img_path
):
raise
Exception
(
"{} does not exist!"
.
format
(
img_path
))
with
open
(
data
[
'img_path'
],
'rb'
)
as
f
:
with
open
(
data
[
'img_path'
],
'rb'
)
as
f
:
img
=
f
.
read
()
img
=
f
.
read
()
data
[
'image'
]
=
img
data
[
'image'
]
=
img
...
@@ -120,8 +113,8 @@ class SimpleDataSet(Dataset):
...
@@ -120,8 +113,8 @@ class SimpleDataSet(Dataset):
except
:
except
:
error_meg
=
traceback
.
format_exc
()
error_meg
=
traceback
.
format_exc
()
self
.
logger
.
error
(
self
.
logger
.
error
(
"When parsing
line
{}, error happened with msg: {}"
.
format
(
"When parsing
file {} and label
{}, error happened with msg: {}"
.
format
(
data
_line
,
error_meg
))
data
[
'img_path'
],
data
[
'label'
]
,
error_meg
))
outs
=
None
outs
=
None
if
outs
is
None
:
if
outs
is
None
:
# during evaluation, we should fix the idx to get same results for many times of evaluation.
# during evaluation, we should fix the idx to get same results for many times of evaluation.
...
@@ -132,3 +125,17 @@ class SimpleDataSet(Dataset):
...
@@ -132,3 +125,17 @@ class SimpleDataSet(Dataset):
def
__len__
(
self
):
def
__len__
(
self
):
return
len
(
self
.
data_idx_order_list
)
return
len
(
self
.
data_idx_order_list
)
def
check_data
(
self
):
new_data_lines
=
[]
for
data_line
in
self
.
data_lines
:
data_line
=
data_line
.
decode
(
'utf-8'
)
substr
=
data_line
.
strip
(
"
\n
"
).
strip
(
"
\r
"
).
split
(
self
.
delimiter
)
file_name
=
substr
[
0
]
label
=
substr
[
1
]
img_path
=
os
.
path
.
join
(
self
.
data_dir
,
file_name
)
if
os
.
path
.
exists
(
img_path
):
new_data_lines
.
append
({
'img_path'
:
img_path
,
'label'
:
label
})
else
:
self
.
logger
.
info
(
"{} does not exist!"
.
format
(
img_path
))
self
.
data_lines
=
new_data_lines
\ No newline at end of file
tools/infer/utility.py
View file @
07026825
...
@@ -24,9 +24,6 @@ from paddle import inference
...
@@ -24,9 +24,6 @@ from paddle import inference
import
time
import
time
from
ppocr.utils.logging
import
get_logger
from
ppocr.utils.logging
import
get_logger
logger
=
get_logger
()
def
str2bool
(
v
):
def
str2bool
(
v
):
return
v
.
lower
()
in
(
"true"
,
"t"
,
"1"
)
return
v
.
lower
()
in
(
"true"
,
"t"
,
"1"
)
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment