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
PaddleOCR
提交
09e72110
P
PaddleOCR
项目概览
PaddlePaddle
/
PaddleOCR
1 年多 前同步成功
通知
1533
Star
32963
Fork
6643
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
108
列表
看板
标记
里程碑
合并请求
7
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
108
Issue
108
列表
看板
标记
里程碑
合并请求
7
合并请求
7
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
09e72110
编写于
7月 20, 2021
作者:
L
LDOUBLEV
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix bugs and adjust warmup times from 10 to 2 to speed up
上级
e450e32d
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
14 addition
and
10 deletion
+14
-10
tests/test.sh
tests/test.sh
+7
-4
tools/infer/predict_det.py
tools/infer/predict_det.py
+2
-2
tools/infer/predict_rec.py
tools/infer/predict_rec.py
+5
-4
未找到文件。
tests/test.sh
浏览文件 @
09e72110
...
...
@@ -138,8 +138,8 @@ infer_img_dir=$(func_parser_value "${lines[44]}")
save_log_key
=
$(
func_parser_key
"
${
lines
[45]
}
"
)
benchmark_key
=
$(
func_parser_key
"
${
lines
[46]
}
"
)
benchmark_value
=
$(
func_parser_value
"
${
lines
[46]
}
"
)
infer_key
2
=
$(
func_parser_key
"
${
lines
[47]
}
"
)
infer_value
2
=
$(
func_parser_value
"
${
lines
[47]
}
"
)
infer_key
1
=
$(
func_parser_key
"
${
lines
[47]
}
"
)
infer_value
1
=
$(
func_parser_value
"
${
lines
[47]
}
"
)
LOG_PATH
=
"./tests/output"
mkdir
-p
${
LOG_PATH
}
...
...
@@ -169,7 +169,8 @@ function func_inference(){
set_batchsize
=
$(
func_set_params
"
${
batch_size_key
}
"
"
${
batch_size
}
"
)
set_cpu_threads
=
$(
func_set_params
"
${
cpu_threads_key
}
"
"
${
threads
}
"
)
set_model_dir
=
$(
func_set_params
"
${
infer_model_key
}
"
"
${
_model_dir
}
"
)
command
=
"
${
_python
}
${
_script
}
${
use_gpu_key
}
=
${
use_gpu
}
${
use_mkldnn_key
}
=
${
use_mkldnn
}
${
set_cpu_threads
}
${
set_model_dir
}
${
set_batchsize
}
${
set_infer_data
}
${
set_benchmark
}
>
${
_save_log_path
}
2>&1 "
set_infer_params1
=
$(
func_set_params
"
${
infer_key1
}
"
"
${
infer_value1
}
"
)
command
=
"
${
_python
}
${
_script
}
${
use_gpu_key
}
=
${
use_gpu
}
${
use_mkldnn_key
}
=
${
use_mkldnn
}
${
set_cpu_threads
}
${
set_model_dir
}
${
set_batchsize
}
${
set_infer_data
}
${
set_benchmark
}
${
set_infer_params1
}
>
${
_save_log_path
}
2>&1 "
eval
$command
status_check
$?
"
${
command
}
"
"
${
status_log
}
"
done
...
...
@@ -285,7 +286,8 @@ for gpu in ${gpu_list[*]}; do
set_eval_pretrain
=
$(
func_set_params
"
${
pretrain_model_key
}
"
"
${
save_log
}
/
${
train_model_name
}
"
)
# run eval
if
[
${
eval_py
}
!=
"null"
]
;
then
eval_cmd
=
"
${
python
}
${
eval_py
}
${
set_eval_pretrain
}
${
set_use_gpu
}
"
set_eval_params1
=
$(
func_set_params
"
${
eval_key1
}
"
"
${
eval_value1
}
"
)
eval_cmd
=
"
${
python
}
${
eval_py
}
${
set_eval_pretrain
}
${
set_use_gpu
}
${
set_eval_params1
}
"
eval
$eval_cmd
status_check
$?
"
${
eval_cmd
}
"
"
${
status_log
}
"
fi
...
...
@@ -318,3 +320,4 @@ else
#run inference
func_inference
"
${
python
}
"
"
${
inference_py
}
"
"
${
infer_model
}
"
"
${
LOG_PATH
}
"
"
${
infer_img_dir
}
"
"False"
fi
tools/infer/predict_det.py
浏览文件 @
09e72110
...
...
@@ -114,7 +114,7 @@ class TextDetector(object):
time_keys
=
[
'preprocess_time'
,
'inference_time'
,
'postprocess_time'
],
warmup
=
10
,
warmup
=
2
,
logger
=
logger
)
def
order_points_clockwise
(
self
,
pts
):
...
...
@@ -237,7 +237,7 @@ if __name__ == "__main__":
if
args
.
warmup
:
img
=
np
.
random
.
uniform
(
0
,
255
,
[
640
,
640
,
3
]).
astype
(
np
.
uint8
)
for
i
in
range
(
10
):
for
i
in
range
(
2
):
res
=
text_detector
(
img
)
if
not
os
.
path
.
exists
(
draw_img_save
):
...
...
tools/infer/predict_rec.py
浏览文件 @
09e72110
...
...
@@ -73,7 +73,7 @@ class TextRecognizer(object):
model_precision
=
args
.
precision
,
batch_size
=
args
.
rec_batch_num
,
data_shape
=
"dynamic"
,
save_path
=
args
.
save_log_path
,
save_path
=
None
,
#
args.save_log_path,
inference_config
=
self
.
config
,
pids
=
pid
,
process_name
=
None
,
...
...
@@ -81,7 +81,8 @@ class TextRecognizer(object):
time_keys
=
[
'preprocess_time'
,
'inference_time'
,
'postprocess_time'
],
warmup
=
10
)
warmup
=
2
,
logger
=
logger
)
def
resize_norm_img
(
self
,
img
,
max_wh_ratio
):
imgC
,
imgH
,
imgW
=
self
.
rec_image_shape
...
...
@@ -272,10 +273,10 @@ def main(args):
valid_image_file_list
=
[]
img_list
=
[]
# warmup
10
times
# warmup
2
times
if
args
.
warmup
:
img
=
np
.
random
.
uniform
(
0
,
255
,
[
32
,
320
,
3
]).
astype
(
np
.
uint8
)
for
i
in
range
(
10
):
for
i
in
range
(
2
):
res
=
text_recognizer
([
img
])
for
image_file
in
image_file_list
:
...
...
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