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
聚火科技码农
PaddleOCR
提交
24757ba6
P
PaddleOCR
项目概览
聚火科技码农
/
PaddleOCR
与 Fork 源项目一致
Fork自
PaddlePaddle / PaddleOCR
通知
1
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
PaddleOCR
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
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
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 >>
提交
24757ba6
编写于
6月 02, 2020
作者:
T
tink2123
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
modified infer single
上级
dab609b1
变更
17
显示空白变更内容
内联
并排
Showing
17 changed file
with
43 addition
and
32 deletion
+43
-32
configs/rec/rec_benchmark_reader.yml
configs/rec/rec_benchmark_reader.yml
+0
-1
configs/rec/rec_chinese_lite_train.yml
configs/rec/rec_chinese_lite_train.yml
+2
-0
configs/rec/rec_chinese_reader.yml
configs/rec/rec_chinese_reader.yml
+0
-1
configs/rec/rec_icdar15_reader.yml
configs/rec/rec_icdar15_reader.yml
+0
-1
configs/rec/rec_icdar15_train.yml
configs/rec/rec_icdar15_train.yml
+2
-0
configs/rec/rec_mv3_none_bilstm_ctc.yml
configs/rec/rec_mv3_none_bilstm_ctc.yml
+2
-2
configs/rec/rec_mv3_none_none_ctc.yml
configs/rec/rec_mv3_none_none_ctc.yml
+1
-0
configs/rec/rec_mv3_tps_bilstm_attn.yml
configs/rec/rec_mv3_tps_bilstm_attn.yml
+3
-1
configs/rec/rec_mv3_tps_bilstm_ctc.yml
configs/rec/rec_mv3_tps_bilstm_ctc.yml
+1
-0
configs/rec/rec_r34_vd_none_bilstm_ctc.yml
configs/rec/rec_r34_vd_none_bilstm_ctc.yml
+3
-1
configs/rec/rec_r34_vd_none_none_ctc.yml
configs/rec/rec_r34_vd_none_none_ctc.yml
+1
-0
configs/rec/rec_r34_vd_tps_bilstm_attn.yml
configs/rec/rec_r34_vd_tps_bilstm_attn.yml
+2
-0
configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
+2
-0
doc/recognition.md
doc/recognition.md
+1
-1
ppocr/data/rec/dataset_traversal.py
ppocr/data/rec/dataset_traversal.py
+14
-16
tools/eval_utils/eval_rec_utils.py
tools/eval_utils/eval_rec_utils.py
+4
-4
tools/infer_rec.py
tools/infer_rec.py
+5
-4
未找到文件。
configs/rec/rec_benchmark_reader.yml
浏览文件 @
24757ba6
...
...
@@ -10,4 +10,3 @@ EvalReader:
TestReader
:
reader_function
:
ppocr.data.rec.dataset_traversal,LMDBReader
lmdb_sets_dir
:
./train_data/data_lmdb_release/evaluation/
infer_img
:
./infer_img
configs/rec/rec_chinese_lite_train.yml
浏览文件 @
24757ba6
...
...
@@ -18,6 +18,8 @@ Global:
pretrain_weights
:
checkpoints
:
save_inference_dir
:
infer_img
:
Architecture
:
function
:
ppocr.modeling.architectures.rec_model,RecModel
...
...
configs/rec/rec_chinese_reader.yml
浏览文件 @
24757ba6
...
...
@@ -11,4 +11,3 @@ EvalReader:
TestReader
:
reader_function
:
ppocr.data.rec.dataset_traversal,SimpleReader
infer_img
:
./infer_img
configs/rec/rec_icdar15_reader.yml
浏览文件 @
24757ba6
...
...
@@ -11,4 +11,3 @@ EvalReader:
TestReader
:
reader_function
:
ppocr.data.rec.dataset_traversal,SimpleReader
infer_img
:
./infer_img
configs/rec/rec_icdar15_train.yml
浏览文件 @
24757ba6
...
...
@@ -17,6 +17,8 @@ Global:
pretrain_weights
:
./pretrain_models/rec_mv3_none_bilstm_ctc/best_accuracy
checkpoints
:
save_inference_dir
:
infer_img
:
Architecture
:
function
:
ppocr.modeling.architectures.rec_model,RecModel
...
...
configs/rec/rec_mv3_none_bilstm_ctc.yml
浏览文件 @
24757ba6
Global
:
algorithm
:
CRNN
use_gpu
:
tru
e
use_gpu
:
fals
e
epoch_num
:
72
log_smooth_window
:
20
print_batch_step
:
10
...
...
@@ -14,7 +14,7 @@ Global:
character_type
:
en
loss_type
:
ctc
reader_yml
:
./configs/rec/rec_benchmark_reader.yml
pretrain_weights
:
pretrain_weights
:
./output/rec_CRNN/rec_mv3_none_bilstm_ctc/best_accuracy
checkpoints
:
save_inference_dir
:
...
...
configs/rec/rec_mv3_none_none_ctc.yml
浏览文件 @
24757ba6
...
...
@@ -17,6 +17,7 @@ Global:
pretrain_weights
:
checkpoints
:
save_inference_dir
:
infer_img
:
Architecture
:
function
:
ppocr.modeling.architectures.rec_model,RecModel
...
...
configs/rec/rec_mv3_tps_bilstm_attn.yml
浏览文件 @
24757ba6
...
...
@@ -17,6 +17,8 @@ Global:
pretrain_weights
:
checkpoints
:
save_inference_dir
:
infer_img
:
Architecture
:
function
:
ppocr.modeling.architectures.rec_model,RecModel
...
...
configs/rec/rec_mv3_tps_bilstm_ctc.yml
浏览文件 @
24757ba6
...
...
@@ -17,6 +17,7 @@ Global:
pretrain_weights
:
checkpoints
:
save_inference_dir
:
infer_img
:
Architecture
:
...
...
configs/rec/rec_r34_vd_none_bilstm_ctc.yml
浏览文件 @
24757ba6
...
...
@@ -17,6 +17,8 @@ Global:
pretrain_weights
:
checkpoints
:
save_inference_dir
:
infer_img
:
Architecture
:
function
:
ppocr.modeling.architectures.rec_model,RecModel
...
...
configs/rec/rec_r34_vd_none_none_ctc.yml
浏览文件 @
24757ba6
...
...
@@ -17,6 +17,7 @@ Global:
pretrain_weights
:
checkpoints
:
save_inference_dir
:
infer_img
:
Architecture
:
function
:
ppocr.modeling.architectures.rec_model,RecModel
...
...
configs/rec/rec_r34_vd_tps_bilstm_attn.yml
浏览文件 @
24757ba6
...
...
@@ -17,6 +17,8 @@ Global:
pretrain_weights
:
checkpoints
:
save_inference_dir
:
infer_img
:
Architecture
:
function
:
ppocr.modeling.architectures.rec_model,RecModel
...
...
configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
浏览文件 @
24757ba6
...
...
@@ -17,6 +17,8 @@ Global:
pretrain_weights
:
checkpoints
:
save_inference_dir
:
infer_img
:
Architecture
:
function
:
ppocr.modeling.architectures.rec_model,RecModel
...
...
doc/recognition.md
浏览文件 @
24757ba6
...
...
@@ -184,7 +184,7 @@ python3 tools/eval.py -c configs/rec/rec_chinese_lite_train.yml -o Global.checkp
```
# 预测英文结果
python3 tools/infer_rec.py -c configs/rec/rec_chinese_lite_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy
TestReader.infer_img=doc/imgs_words/en/word_1.jp
g
python3 tools/infer_rec.py -c configs/rec/rec_chinese_lite_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy
Global.infer_img=doc/imgs_words/en/word_1.pn
g
```
预测图片:
...
...
ppocr/data/rec/dataset_traversal.py
浏览文件 @
24757ba6
...
...
@@ -43,11 +43,10 @@ class LMDBReader(object):
self
.
mode
=
params
[
'mode'
]
if
params
[
'mode'
]
==
'train'
:
self
.
batch_size
=
params
[
'train_batch_size_per_card'
]
el
if
params
[
'mode'
]
==
"eval"
:
el
se
:
self
.
batch_size
=
params
[
'test_batch_size_per_card'
]
elif
params
[
'mode'
]
==
"test"
:
self
.
batch_size
=
1
self
.
infer_img
=
params
[
"infer_img"
]
self
.
infer_img
=
params
[
'infer_img'
]
def
load_hierarchical_lmdb_dataset
(
self
):
lmdb_sets
=
{}
dataset_idx
=
0
...
...
@@ -100,11 +99,11 @@ class LMDBReader(object):
process_id
=
0
def
sample_iter_reader
():
if
self
.
mode
==
'test'
:
if
self
.
infer_img
is
not
None
:
image_file_list
=
get_image_file_list
(
self
.
infer_img
)
for
single_img
in
image_file_list
:
img
=
cv2
.
imread
(
single_img
)
if
img
.
shape
[
-
1
]
==
1
or
len
(
list
(
img
.
shape
))
==
2
:
if
img
.
shape
[
-
1
]
==
1
or
len
(
list
(
img
.
shape
))
==
2
:
img
=
cv2
.
cvtColor
(
img
,
cv2
.
COLOR_GRAY2BGR
)
norm_img
=
process_image
(
img
,
self
.
image_shape
)
yield
norm_img
...
...
@@ -136,6 +135,7 @@ class LMDBReader(object):
if
finish_read_num
==
len
(
lmdb_sets
):
break
self
.
close_lmdb_dataset
(
lmdb_sets
)
def
batch_iter_reader
():
batch_outs
=
[]
for
outs
in
sample_iter_reader
():
...
...
@@ -146,7 +146,7 @@ class LMDBReader(object):
if
len
(
batch_outs
)
!=
0
:
yield
batch_outs
if
self
.
mode
!=
'test'
:
if
self
.
infer_img
is
None
:
return
batch_iter_reader
return
sample_iter_reader
...
...
@@ -165,24 +165,22 @@ class SimpleReader(object):
self
.
loss_type
=
params
[
'loss_type'
]
self
.
max_text_length
=
params
[
'max_text_length'
]
self
.
mode
=
params
[
'mode'
]
self
.
infer_img
=
params
[
'infer_img'
]
if
params
[
'mode'
]
==
'train'
:
self
.
batch_size
=
params
[
'train_batch_size_per_card'
]
elif
params
[
'mode'
]
==
'eval'
:
self
.
batch_size
=
params
[
'test_batch_size_per_card'
]
else
:
self
.
batch_size
=
1
self
.
infer_img
=
params
[
'infer_img'
]
self
.
batch_size
=
params
[
'test_batch_size_per_card'
]
def
__call__
(
self
,
process_id
):
if
self
.
mode
!=
'train'
:
process_id
=
0
def
sample_iter_reader
():
if
self
.
mode
==
'test'
:
if
self
.
infer_img
is
not
None
:
image_file_list
=
get_image_file_list
(
self
.
infer_img
)
for
single_img
in
image_file_list
:
img
=
cv2
.
imread
(
single_img
)
if
img
.
shape
[
-
1
]
==
1
or
len
(
list
(
img
.
shape
))
==
2
:
if
img
.
shape
[
-
1
]
==
1
or
len
(
list
(
img
.
shape
))
==
2
:
img
=
cv2
.
cvtColor
(
img
,
cv2
.
COLOR_GRAY2BGR
)
norm_img
=
process_image
(
img
,
self
.
image_shape
)
yield
norm_img
...
...
@@ -192,7 +190,7 @@ class SimpleReader(object):
img_num
=
len
(
label_infor_list
)
img_id_list
=
list
(
range
(
img_num
))
random
.
shuffle
(
img_id_list
)
if
sys
.
platform
==
"win32"
:
if
sys
.
platform
==
"win32"
:
print
(
"multiprocess is not fully compatible with Windows."
"num_workers will be 1."
)
self
.
num_workers
=
1
...
...
@@ -204,7 +202,7 @@ class SimpleReader(object):
if
img
is
None
:
logger
.
info
(
"{} does not exist!"
.
format
(
img_path
))
continue
if
img
.
shape
[
-
1
]
==
1
or
len
(
list
(
img
.
shape
))
==
2
:
if
img
.
shape
[
-
1
]
==
1
or
len
(
list
(
img
.
shape
))
==
2
:
img
=
cv2
.
cvtColor
(
img
,
cv2
.
COLOR_GRAY2BGR
)
label
=
substr
[
1
]
...
...
@@ -225,6 +223,6 @@ class SimpleReader(object):
if
len
(
batch_outs
)
!=
0
:
yield
batch_outs
if
self
.
mode
!=
'test'
:
if
self
.
infer_img
is
None
:
return
batch_iter_reader
return
sample_iter_reader
tools/eval_utils/eval_rec_utils.py
浏览文件 @
24757ba6
...
...
@@ -48,7 +48,7 @@ def eval_rec_run(exe, config, eval_info_dict, mode):
total_sample_num
=
0
total_acc_num
=
0
total_batch_num
=
0
if
mode
==
"
test
"
:
if
mode
==
"
eval
"
:
is_remove_duplicate
=
False
else
:
is_remove_duplicate
=
True
...
...
@@ -91,11 +91,11 @@ def test_rec_benchmark(exe, config, eval_info_dict):
total_correct_number
=
0
eval_data_acc_info
=
{}
for
eval_data
in
eval_data_list
:
config
[
'
Eval
Reader'
][
'lmdb_sets_dir'
]
=
\
config
[
'
Test
Reader'
][
'lmdb_sets_dir'
]
=
\
eval_data_dir
+
"/"
+
eval_data
eval_reader
=
reader_main
(
config
=
config
,
mode
=
"
eval
"
)
eval_reader
=
reader_main
(
config
=
config
,
mode
=
"
test
"
)
eval_info_dict
[
'reader'
]
=
eval_reader
metrics
=
eval_rec_run
(
exe
,
config
,
eval_info_dict
,
"
eval
"
)
metrics
=
eval_rec_run
(
exe
,
config
,
eval_info_dict
,
"
test
"
)
total_evaluation_data_number
+=
metrics
[
'total_sample_num'
]
total_correct_number
+=
metrics
[
'total_acc_num'
]
eval_data_acc_info
[
eval_data
]
=
metrics
...
...
tools/infer_rec.py
浏览文件 @
24757ba6
...
...
@@ -21,6 +21,7 @@ import time
import
multiprocessing
import
numpy
as
np
def
set_paddle_flags
(
**
kwargs
):
for
key
,
value
in
kwargs
.
items
():
if
os
.
environ
.
get
(
key
,
None
)
is
None
:
...
...
@@ -78,13 +79,13 @@ def main():
init_model
(
config
,
eval_prog
,
exe
)
blobs
=
reader_main
(
config
,
'test'
)()
infer_img
=
config
[
'
TestReader
'
][
'infer_img'
]
infer_img
=
config
[
'
Global
'
][
'infer_img'
]
infer_list
=
get_image_file_list
(
infer_img
)
max_img_num
=
len
(
infer_list
)
if
len
(
infer_list
)
==
0
:
logger
.
info
(
"Can not find img in infer_img dir."
)
for
i
in
range
(
max_img_num
):
print
(
"infer_img:"
,
infer_list
[
i
])
print
(
"infer_img:"
,
infer_list
[
i
])
img
=
next
(
blobs
)
predict
=
exe
.
run
(
program
=
eval_prog
,
feed
=
{
"image"
:
img
},
...
...
@@ -105,8 +106,8 @@ def main():
preds_text
=
preds_text
.
reshape
(
-
1
)
preds_text
=
char_ops
.
decode
(
preds_text
)
print
(
"
\t
index:"
,
preds
)
print
(
"
\t
word :"
,
preds_text
)
print
(
"
\t
index:"
,
preds
)
print
(
"
\t
word :"
,
preds_text
)
# save for inference model
target_var
=
[]
...
...
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