diff --git a/README_ch.md b/README_ch.md
index fb0ebdab40b362178b1b520b804f81c5ccc61ddd..fa400d31307e83831628bc45559845e7adef6ffd 100644
--- a/README_ch.md
+++ b/README_ch.md
@@ -97,6 +97,9 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 - [许可证书](#许可证书)
 - [贡献代码](#贡献代码)
 
+***注意：动态图端侧部署仍在开发中，目前仅支持动态图训练、python端预测，C++预测，
+如果您有需要移动端部署案例或者量化裁剪，请切换到静态图分支；***
+
 <a name="PP-OCR"></a>
 ## PP-OCR Pipline
 <div align="center">
diff --git a/README_en.md b/README_en.md
index 6552aab5fa8e249b91bb9f52386ecdac18f04f7c..0b5eb1c60b5591c889275f31f4d5952727ae7645 100644
--- a/README_en.md
+++ b/README_en.md
@@ -108,6 +108,12 @@ For a new language request, please refer to [Guideline for new language_requests
 - [License](#LICENSE)
 - [Contribution](#CONTRIBUTION)
 
+***Note: The dynamic graphs branch is still under development.
+Currently, only dynamic graph training, python-end prediction, and C++ prediction are supported.
+If you need mobile-end deployment cases or quantitative demo,
+please use the static graph branch.***
+
+
 <a name="PP-OCR-Pipeline"></a>
 
 ## PP-OCR Pipeline