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
邱崇源
PaddleOCR
提交
9126cb6f
P
PaddleOCR
项目概览
邱崇源
/
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
9126cb6f
编写于
5月 13, 2020
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
modify rec saved model dir
上级
8007a955
变更
9
隐藏空白更改
内联
并排
Showing
9 changed file
with
9 addition
and
11 deletion
+9
-11
configs/rec/rec_mv3_none_bilstm_ctc.yml
configs/rec/rec_mv3_none_bilstm_ctc.yml
+1
-1
configs/rec/rec_mv3_none_none_ctc.yml
configs/rec/rec_mv3_none_none_ctc.yml
+1
-1
configs/rec/rec_mv3_tps_bilstm_attn.yml
configs/rec/rec_mv3_tps_bilstm_attn.yml
+1
-1
configs/rec/rec_mv3_tps_bilstm_ctc.yml
configs/rec/rec_mv3_tps_bilstm_ctc.yml
+1
-1
configs/rec/rec_r34_vd_none_bilstm_ctc.yml
configs/rec/rec_r34_vd_none_bilstm_ctc.yml
+1
-1
configs/rec/rec_r34_vd_none_none_ctc.yml
configs/rec/rec_r34_vd_none_none_ctc.yml
+1
-1
configs/rec/rec_r34_vd_tps_bilstm_attn.yml
configs/rec/rec_r34_vd_tps_bilstm_attn.yml
+1
-1
configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
+1
-1
tools/program.py
tools/program.py
+1
-3
未找到文件。
configs/rec/rec_mv3_none_bilstm_ctc.yml
浏览文件 @
9126cb6f
...
@@ -4,7 +4,7 @@ Global:
...
@@ -4,7 +4,7 @@ Global:
epoch_num
:
72
epoch_num
:
72
log_smooth_window
:
20
log_smooth_window
:
20
print_batch_step
:
10
print_batch_step
:
10
save_model_dir
:
output/rec
save_model_dir
:
output/rec
_CRNN
save_epoch_step
:
3
save_epoch_step
:
3
eval_batch_step
:
2000
eval_batch_step
:
2000
train_batch_size_per_card
:
256
train_batch_size_per_card
:
256
...
...
configs/rec/rec_mv3_none_none_ctc.yml
浏览文件 @
9126cb6f
...
@@ -4,7 +4,7 @@ Global:
...
@@ -4,7 +4,7 @@ Global:
epoch_num
:
72
epoch_num
:
72
log_smooth_window
:
20
log_smooth_window
:
20
print_batch_step
:
10
print_batch_step
:
10
save_model_dir
:
output/rec
save_model_dir
:
output/rec
_Rosetta
save_epoch_step
:
3
save_epoch_step
:
3
eval_batch_step
:
2000
eval_batch_step
:
2000
train_batch_size_per_card
:
256
train_batch_size_per_card
:
256
...
...
configs/rec/rec_mv3_tps_bilstm_attn.yml
浏览文件 @
9126cb6f
...
@@ -4,7 +4,7 @@ Global:
...
@@ -4,7 +4,7 @@ Global:
epoch_num
:
72
epoch_num
:
72
log_smooth_window
:
20
log_smooth_window
:
20
print_batch_step
:
10
print_batch_step
:
10
save_model_dir
:
output/rec
save_model_dir
:
output/rec
_RARE
save_epoch_step
:
3
save_epoch_step
:
3
eval_batch_step
:
2000
eval_batch_step
:
2000
train_batch_size_per_card
:
256
train_batch_size_per_card
:
256
...
...
configs/rec/rec_mv3_tps_bilstm_ctc.yml
浏览文件 @
9126cb6f
...
@@ -4,7 +4,7 @@ Global:
...
@@ -4,7 +4,7 @@ Global:
epoch_num
:
72
epoch_num
:
72
log_smooth_window
:
20
log_smooth_window
:
20
print_batch_step
:
10
print_batch_step
:
10
save_model_dir
:
output/rec
save_model_dir
:
output/rec
_STARNet
save_epoch_step
:
3
save_epoch_step
:
3
eval_batch_step
:
2000
eval_batch_step
:
2000
train_batch_size_per_card
:
256
train_batch_size_per_card
:
256
...
...
configs/rec/rec_r34_vd_none_bilstm_ctc.yml
浏览文件 @
9126cb6f
...
@@ -4,7 +4,7 @@ Global:
...
@@ -4,7 +4,7 @@ Global:
epoch_num
:
72
epoch_num
:
72
log_smooth_window
:
20
log_smooth_window
:
20
print_batch_step
:
10
print_batch_step
:
10
save_model_dir
:
output/rec
save_model_dir
:
output/rec
_CRNN
save_epoch_step
:
3
save_epoch_step
:
3
eval_batch_step
:
2000
eval_batch_step
:
2000
train_batch_size_per_card
:
256
train_batch_size_per_card
:
256
...
...
configs/rec/rec_r34_vd_none_none_ctc.yml
浏览文件 @
9126cb6f
...
@@ -4,7 +4,7 @@ Global:
...
@@ -4,7 +4,7 @@ Global:
epoch_num
:
72
epoch_num
:
72
log_smooth_window
:
20
log_smooth_window
:
20
print_batch_step
:
10
print_batch_step
:
10
save_model_dir
:
output/rec
save_model_dir
:
output/rec
_Rosetta
save_epoch_step
:
3
save_epoch_step
:
3
eval_batch_step
:
2000
eval_batch_step
:
2000
train_batch_size_per_card
:
256
train_batch_size_per_card
:
256
...
...
configs/rec/rec_r34_vd_tps_bilstm_attn.yml
浏览文件 @
9126cb6f
...
@@ -4,7 +4,7 @@ Global:
...
@@ -4,7 +4,7 @@ Global:
epoch_num
:
72
epoch_num
:
72
log_smooth_window
:
20
log_smooth_window
:
20
print_batch_step
:
10
print_batch_step
:
10
save_model_dir
:
output/rec
save_model_dir
:
output/rec
_RARE
save_epoch_step
:
3
save_epoch_step
:
3
eval_batch_step
:
2000
eval_batch_step
:
2000
train_batch_size_per_card
:
256
train_batch_size_per_card
:
256
...
...
configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
浏览文件 @
9126cb6f
...
@@ -4,7 +4,7 @@ Global:
...
@@ -4,7 +4,7 @@ Global:
epoch_num
:
72
epoch_num
:
72
log_smooth_window
:
20
log_smooth_window
:
20
print_batch_step
:
10
print_batch_step
:
10
save_model_dir
:
output/rec
save_model_dir
:
output/rec
_STARNet
save_epoch_step
:
3
save_epoch_step
:
3
eval_batch_step
:
2000
eval_batch_step
:
2000
train_batch_size_per_card
:
256
train_batch_size_per_card
:
256
...
...
tools/program.py
浏览文件 @
9126cb6f
...
@@ -284,9 +284,7 @@ def train_eval_rec_run(config, exe, train_info_dict, eval_info_dict):
...
@@ -284,9 +284,7 @@ def train_eval_rec_run(config, exe, train_info_dict, eval_info_dict):
eval_batch_step
=
config
[
'Global'
][
'eval_batch_step'
]
eval_batch_step
=
config
[
'Global'
][
'eval_batch_step'
]
save_epoch_step
=
config
[
'Global'
][
'save_epoch_step'
]
save_epoch_step
=
config
[
'Global'
][
'save_epoch_step'
]
save_model_dir
=
config
[
'Global'
][
'save_model_dir'
]
save_model_dir
=
config
[
'Global'
][
'save_model_dir'
]
if
save_model_dir
[
-
1
]
==
"/"
:
if
not
os
.
path
.
exists
(
save_model_dir
):
save_model_dir
=
save_model_dir
[:
-
1
]
if
not
os
.
path
.
exists
(
save_model_dir
+
config
[
'Global'
][
'algorithm'
]):
os
.
makedirs
(
save_model_dir
)
os
.
makedirs
(
save_model_dir
)
train_stats
=
TrainingStats
(
log_smooth_window
,
[
'loss'
,
'acc'
])
train_stats
=
TrainingStats
(
log_smooth_window
,
[
'loss'
,
'acc'
])
best_eval_acc
=
-
1
best_eval_acc
=
-
1
...
...
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