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
恒星小白
PaddleOCR
提交
0938c44a
P
PaddleOCR
项目概览
恒星小白
/
PaddleOCR
与 Fork 源项目一致
Fork自
PaddlePaddle / PaddleOCR
通知
2
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 >>
未验证
提交
0938c44a
编写于
6月 17, 2021
作者:
L
littletomatodonkey
提交者:
GitHub
6月 17, 2021
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add embedding and fix eval when distillation (#3112)
上级
56ab75b0
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
50 addition
and
13 deletion
+50
-13
configs/rec/ch_ppocr_v2.1/rec_chinese_lite_train_distillation_v2.1.yml
...h_ppocr_v2.1/rec_chinese_lite_train_distillation_v2.1.yml
+4
-2
ppocr/modeling/heads/rec_ctc_head.py
ppocr/modeling/heads/rec_ctc_head.py
+37
-9
tools/eval.py
tools/eval.py
+9
-2
未找到文件。
configs/rec/ch_ppocr_v2.1/rec_chinese_lite_train_distillation_v2.1.yml
浏览文件 @
0938c44a
...
...
@@ -52,9 +52,10 @@ Architecture:
Neck
:
name
:
SequenceEncoder
encoder_type
:
rnn
hidden_size
:
48
hidden_size
:
64
Head
:
name
:
CTCHead
mid_channels
:
96
fc_decay
:
0.00001
Teacher
:
pretrained
:
...
...
@@ -71,9 +72,10 @@ Architecture:
Neck
:
name
:
SequenceEncoder
encoder_type
:
rnn
hidden_size
:
48
hidden_size
:
64
Head
:
name
:
CTCHead
mid_channels
:
96
fc_decay
:
0.00001
...
...
ppocr/modeling/heads/rec_ctc_head.py
浏览文件 @
0938c44a
...
...
@@ -33,19 +33,47 @@ def get_para_bias_attr(l2_decay, k):
class
CTCHead
(
nn
.
Layer
):
def
__init__
(
self
,
in_channels
,
out_channels
,
fc_decay
=
0.0004
,
**
kwargs
):
def
__init__
(
self
,
in_channels
,
out_channels
,
fc_decay
=
0.0004
,
mid_channels
=
None
,
**
kwargs
):
super
(
CTCHead
,
self
).
__init__
()
weight_attr
,
bias_attr
=
get_para_bias_attr
(
l2_decay
=
fc_decay
,
k
=
in_channels
)
self
.
fc
=
nn
.
Linear
(
in_channels
,
out_channels
,
weight_attr
=
weight_attr
,
bias_attr
=
bias_attr
)
if
mid_channels
is
None
:
weight_attr
,
bias_attr
=
get_para_bias_attr
(
l2_decay
=
fc_decay
,
k
=
in_channels
)
self
.
fc
=
nn
.
Linear
(
in_channels
,
out_channels
,
weight_attr
=
weight_attr
,
bias_attr
=
bias_attr
)
else
:
weight_attr1
,
bias_attr1
=
get_para_bias_attr
(
l2_decay
=
fc_decay
,
k
=
in_channels
)
self
.
fc1
=
nn
.
Linear
(
in_channels
,
mid_channels
,
weight_attr
=
weight_attr1
,
bias_attr
=
bias_attr1
)
weight_attr2
,
bias_attr2
=
get_para_bias_attr
(
l2_decay
=
fc_decay
,
k
=
mid_channels
)
self
.
fc2
=
nn
.
Linear
(
mid_channels
,
out_channels
,
weight_attr
=
weight_attr2
,
bias_attr
=
bias_attr2
)
self
.
out_channels
=
out_channels
self
.
mid_channels
=
mid_channels
def
forward
(
self
,
x
,
labels
=
None
):
predicts
=
self
.
fc
(
x
)
if
self
.
mid_channels
is
None
:
predicts
=
self
.
fc
(
x
)
else
:
predicts
=
self
.
fc1
(
x
)
predicts
=
self
.
fc2
(
predicts
)
if
not
self
.
training
:
predicts
=
F
.
softmax
(
predicts
,
axis
=
2
)
return
predicts
tools/eval.py
浏览文件 @
0938c44a
...
...
@@ -44,8 +44,15 @@ def main():
# build model
# for rec algorithm
if
hasattr
(
post_process_class
,
'character'
):
config
[
'Architecture'
][
"Head"
][
'out_channels'
]
=
len
(
getattr
(
post_process_class
,
'character'
))
char_num
=
len
(
getattr
(
post_process_class
,
'character'
))
if
config
[
'Architecture'
][
"algorithm"
]
in
[
"Distillation"
,
]:
# distillation model
for
key
in
config
[
'Architecture'
][
"Models"
]:
config
[
'Architecture'
][
"Models"
][
key
][
"Head"
][
'out_channels'
]
=
char_num
else
:
# base rec model
config
[
'Architecture'
][
"Head"
][
'out_channels'
]
=
char_num
model
=
build_model
(
config
[
'Architecture'
])
use_srn
=
config
[
'Architecture'
][
'algorithm'
]
==
"SRN"
...
...
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