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
0b8c6f1f
Commit
0b8c6f1f
authored
May 05, 2022
by
LDOUBLEV
Browse files
fix
parent
4c129c77
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
1 deletion
+1
-1
doc/doc_ch/PP-OCRv3_introduction.md
doc/doc_ch/PP-OCRv3_introduction.md
+1
-1
No files found.
doc/doc_ch/PP-OCRv3_introduction.md
View file @
0b8c6f1f
...
@@ -36,7 +36,7 @@ PP-OCR从骨干网络选择和调整、预测头部的设计、数据增强、
...
@@ -36,7 +36,7 @@ PP-OCR从骨干网络选择和调整、预测头部的设计、数据增强、
PP-OCRv3采用PP-OCRv2的
[
CML
](
https://arxiv.org/pdf/2109.03144.pdf
)
蒸馏策略,在蒸馏的student模型、teacher模型精度提升,CML蒸馏策略上分别做了优化。
PP-OCRv3采用PP-OCRv2的
[
CML
](
https://arxiv.org/pdf/2109.03144.pdf
)
蒸馏策略,在蒸馏的student模型、teacher模型精度提升,CML蒸馏策略上分别做了优化。
-
在蒸馏student模型精度提升方面,提出了
PP-OCRv2的FPN结构改进版
RSEFPN(Residual Squeeze-and-Excitation FPN),用于提升student模型精度和召回。
-
在蒸馏student模型精度提升方面,提出了
基于残差结构的通道注意力模块
RSEFPN(Residual Squeeze-and-Excitation FPN),用于提升student模型精度和召回。
RSEFPN的网络结构如下图所示,RSEFPN在PP-OCRv2的FPN基础上,将FPN中的卷积层更换为了通道注意力结构的RSEConv层。
RSEFPN的网络结构如下图所示,RSEFPN在PP-OCRv2的FPN基础上,将FPN中的卷积层更换为了通道注意力结构的RSEConv层。
...
...
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