-
+
+
@@ -33,7 +33,7 @@
💖 Introducing the foremost multi-platform, multi-lingual OCR tool that boasts unparalleled speed, expansive support, and complete openness. This exceptional software is entirely free and renowned for facilitating swift offline deployments.
-🦜 **Supported Languages**: It inherently supports Chinese and English, with self-service conversion required for additional languages. Please refer [here](https://rapidai.github.io/RapidOCRDocs/blog/2022/09/28/%E6%94%AF%E6%8C%81%E8%AF%86%E5%88%AB%E8%AF%AD%E8%A8%80/) for specific language support details.
+🦜 **Supported Languages**: It inherently supports Chinese and English, with self-service conversion required for additional languages. Please refer [here](https://rapidai.github.io/RapidOCRDocs/main/blog/2022/09/28/%E6%94%AF%E6%8C%81%E8%AF%86%E5%88%AB%E8%AF%AD%E8%A8%80/) for specific language support details.
🔎 **Rationale**: Acknowledging the limitations in [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)'s architecture, we embarked on a mission to simplify OCR inference across diverse platforms. This endeavor culminated in converting PaddleOCR's model to the versatile ONNX format and seamlessly integrating it into Python, C++, Java, and C# environments.
@@ -46,7 +46,7 @@
If our repository proves beneficial to your endeavors, kindly consider leaving a star ⭐ on GitHub to show your appreciation. It means the world to us!
-### Visualization ([more](https://rapidai.github.io/RapidOCRDocs/visualization/))
+### Visualization
@@ -87,7 +87,7 @@ Used by [link](https://github.com/RapidAI/RapidOCR/discussions/286)
- Many thanks to [zhsunlight](https://github.com/zhsunlight) for the suggestion about parameterized call GPU reasoning and the careful and thoughtful testing.
- Many thanks to [lzh111222334](https://github.com/lzh111222334) for fixing some bugs of rec preprocessing under python version.
- Many thanks to [AutumnSun1996](https://github.com/AutumnSun1996) for the suggestion in the [#42](https://github.com/RapidAI/RapidOCR/issues/42).
-- Many thanks to [DeadWood8](https://github.com/DeadWood8) for providing the [document](https://rapidai.github.io/RapidOCRDocs/install_usage/rapidocr_web/nuitka_package) which packages rapidocr_web to exe by Nuitka.
+- Many thanks to [DeadWood8](https://github.com/DeadWood8) for providing the [document](https://rapidai.github.io/RapidOCRDocs/main/install_usage/rapidocr_web/nuitka_package/) which packages rapidocr_web to exe by Nuitka.
- Many thanks to [Loovelj](https://github.com/Loovelj) for fixing the bug of sorting the text boxes. For details see [issue 75](https://github.com/RapidAI/RapidOCR/issues/75).
### 🎖 Code Contributors
@@ -98,7 +98,7 @@ Used by [link](https://github.com/RapidAI/RapidOCR/discussions/286)
-### [Sponsor](https://rapidai.github.io/RapidOCRDocs/sponsor/)
+### [Sponsor](https://rapidai.github.io/RapidOCRDocs/main/sponsor/)
> [!IMPORTANT]
>
diff --git a/api/README.md b/api/README.md
index 33894ef..7a43c91 100644
--- a/api/README.md
+++ b/api/README.md
@@ -1,3 +1,3 @@
### See [RapidOCRAPI](https://github.com/RapidAI/RapidOCRAPI) for details
-### See [Documentation](https://rapidai.github.io/RapidOCRDocs/install_usage/rapidocr_api/usage/)
+### See [Documentation](https://rapidai.github.io/RapidOCRDocs/main/install_usage/rapidocr_api/usage/)
diff --git a/assets/RapidOCRDemo.ipynb b/assets/RapidOCRDemo.ipynb
index b502b25..08ec1d6 100644
--- a/assets/RapidOCRDemo.ipynb
+++ b/assets/RapidOCRDemo.ipynb
@@ -1 +1,389 @@
-{"cells":[{"cell_type":"markdown","metadata":{"id":"8H17bBI3N-vo"},"source":["\n","\n","## RapidOCR Python Demo\n","\n"]},{"cell_type":"markdown","metadata":{"id":"0qapeJlG6JFJ"},"source":["#### Install rapidocr_onnxruntime"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"sTB1PsMp6XTT","outputId":"c17a3881-b441-4f22-eefe-c0844521c5bc"},"outputs":[{"name":"stdout","output_type":"stream","text":["Looking in indexes: https://pypi.douban.com/simple/\n","Collecting rapidocr_onnxruntime\n"," Downloading https://pypi.doubanio.com/packages/c5/ed/16c0d4c909ea626d35923d913295394f2ff40f605cd4036cb9d8ae7eab62/rapidocr_onnxruntime-1.1.18-py3-none-any.whl (12.3 MB)\n"," ---------------------------------------- 12.3/12.3 MB 2.7 MB/s eta 0:00:00\n","Requirement already satisfied: numpy>=1.19.3 in e:\\anaconda3\\envs\\demo\\lib\\site-packages (from rapidocr_onnxruntime) (1.21.6)\n","Requirement already satisfied: Shapely>=1.7.1 in e:\\anaconda3\\envs\\demo\\lib\\site-packages (from rapidocr_onnxruntime) (1.8.1.post1)\n","Requirement already satisfied: opencv-python>=4.5.1.48 in e:\\anaconda3\\envs\\demo\\lib\\site-packages (from rapidocr_onnxruntime) (4.6.0.66)\n","Requirement already satisfied: six>=1.15.0 in e:\\anaconda3\\envs\\demo\\lib\\site-packages (from rapidocr_onnxruntime) (1.16.0)\n","Requirement already satisfied: onnxruntime>=1.7.0 in e:\\anaconda3\\envs\\demo\\lib\\site-packages (from rapidocr_onnxruntime) (1.10.0)\n","Requirement already satisfied: pyclipper>=1.2.1 in e:\\anaconda3\\envs\\demo\\lib\\site-packages (from rapidocr_onnxruntime) (1.2.1)\n","Requirement already satisfied: protobuf in e:\\anaconda3\\envs\\demo\\lib\\site-packages (from onnxruntime>=1.7.0->rapidocr_onnxruntime) (3.20.0)\n","Requirement already satisfied: flatbuffers in e:\\anaconda3\\envs\\demo\\lib\\site-packages (from onnxruntime>=1.7.0->rapidocr_onnxruntime) (2.0)\n","Installing collected packages: rapidocr_onnxruntime\n","Successfully installed rapidocr_onnxruntime-1.1.18\n"]},{"name":"stderr","output_type":"stream","text":["'wget' �����ڲ����ⲿ���Ҳ���ǿ����еij���\n","���������ļ���\n"]}],"source":["!pip install rapidocr_onnxruntime\n","!wget -O 2.jpg https://pic1.zhimg.com/v2-612e2d58bd9f5f4a99c448a4d626ce86_1440w.jpg?source=172ae18b\n","!wget https://github.com/RapidAI/RapidOCR/releases/download/v1.1.0/FZYTK.TTF"]},{"cell_type":"markdown","metadata":{"id":"PDlCLO_CewSk"},"source":["#### Run"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":359},"id":"bbHGS0emSNTz","outputId":"a1ad3cc8-054d-4bec-a3f3-aed5cb30862f","executionInfo":{"status":"ok","timestamp":1727396511860,"user_tz":-480,"elapsed":4846,"user":{"displayName":"","userId":""}}},"outputs":[{"output_type":"stream","name":"stdout","text":["[[[[660.0, 15.0], [686.0, 14.0], [688.0, 83.0], [662.0, 84.0]], '格招打', 0.8068139], [[[57.0, 134.0], [484.0, 136.0], [484.0, 178.0], [57.0, 176.0]], '这时我看见他的背影，', 0.99692094], [[[60.0, 217.0], [538.0, 217.0], [538.0, 256.0], [60.0, 256.0]], '我的泪很快地流下来了。', 0.9964092], [[[58.0, 294.0], [396.0, 296.0], [396.0, 339.0], [58.0, 337.0]], '我赶紧拭干了泪，', 0.98592407], [[[57.0, 372.0], [257.0, 374.0], [257.0, 420.0], [57.0, 418.0]], '怕他看见，', 0.9982783], [[[58.0, 453.0], [350.0, 455.0], [350.0, 498.0], [58.0, 496.0]], '也怕别人看见。', 0.9979418], [[[68.0, 568.0], [191.0, 568.0], [191.0, 609.0], [68.0, 609.0]], '《背影》', 0.9973544]]\n","[1.1213593499999206, 0.029864072799682617, 0.7594971656799316]\n"]},{"output_type":"execute_result","data":{"text/plain":["ndarray (516, 1000, 3)
array([[[255, 255, 255],\n", + " [255, 255, 255],\n", + " [255, 255, 255],\n", + " ...,\n", + " [255, 255, 255],\n", + " [255, 255, 255],\n", + " [255, 255, 255]],\n", + "\n", + " [[255, 255, 255],\n", + " [255, 255, 255],\n", + " [255, 255, 255],\n", + " ...,\n", + " [255, 255, 255],\n", + " [255, 255, 255],\n", + " [255, 255, 255]],\n", + "\n", + " [[255, 255, 255],\n", + " [255, 255, 255],\n", + " [255, 255, 255],\n", + " ...,\n", + " [255, 255, 255],\n", + " [255, 255, 255],\n", + " [255, 255, 255]],\n", + "\n", + " ...,\n", + "\n", + " [[255, 255, 255],\n", + " [255, 255, 255],\n", + " [255, 255, 255],\n", + " ...,\n", + " [255, 255, 255],\n", + " [255, 255, 255],\n", + " [255, 255, 255]],\n", + "\n", + " [[255, 255, 255],\n", + " [255, 255, 255],\n", + " [255, 255, 255],\n", + " ...,\n", + " [255, 255, 255],\n", + " [255, 255, 255],\n", + " [255, 255, 255]],\n", + "\n", + " [[255, 255, 255],\n", + " [255, 255, 255],\n", + " [255, 255, 255],\n", + " ...,\n", + " [255, 255, 255],\n", + " [255, 255, 255],\n", + " [255, 255, 255]]], dtype=uint8)
-
+
+
@@ -34,7 +34,7 @@
💖目前，我们自豪地推出了运行速度最为迅猛、兼容性最为广泛的多平台多语言OCR工具，它完全开源免费，并支持离线环境下的快速部署。
-🦜 **支持语言概览：** 默认支持中文与英文识别，对于其他语言的识别需求，我们提供了便捷的自助转换方案。具体转换指南，请参见[这里](https://rapidai.github.io/RapidOCRDocs/blog/2022/09/28/%E6%94%AF%E6%8C%81%E8%AF%86%E5%88%AB%E8%AF%AD%E8%A8%80/)。
+🦜 **支持语言概览：** 默认支持中文与英文识别，对于其他语言的识别需求，我们提供了便捷的自助转换方案。具体转换指南，请参见[这里](https://rapidai.github.io/RapidOCRDocs/main/blog/2022/09/28/%E6%94%AF%E6%8C%81%E8%AF%86%E5%88%AB%E8%AF%AD%E8%A8%80/)。
🔎 **项目缘起：** 鉴于[PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)在工程化方面仍有进一步优化的空间，为了简化并加速在各种终端设备上进行OCR推理的过程，我们创新地将PaddleOCR中的模型转换为了高度兼容的ONNX格式，并利用Python、C++、Java、C#等多种编程语言，实现了跨平台的无缝移植，让广大开发者能够轻松上手，高效应用。
@@ -42,12 +42,12 @@
😉 **使用指南：**
-- 直接部署：若本仓库中已提供的模型能满足您的需求，那么您只需参考[官方文档](https://rapidai.github.io/RapidOCRDocs/quickstart/)进行RapidOCR的部署与使用即可。
+- 直接部署：若本仓库中已提供的模型能满足您的需求，那么您只需参考[官方文档](https://rapidai.github.io/RapidOCRDocs/main/quickstart/)进行RapidOCR的部署与使用即可。
- 定制化微调：若现有模型无法满足您的特定需求，您可以在PaddleOCR的基础上，利用自己的数据进行微调，随后再将其应用于RapidOCR的部署中，实现个性化定制。
如果您发现本仓库对您的项目或学习有所助益，恳请您慷慨地给个小星星⭐，给予我们支持与鼓励！
-### 效果展示 ([more](https://rapidai.github.io/RapidOCRDocs/visualization/))
+### 效果展示
@@ -88,7 +88,7 @@ Used by [link](https://github.com/RapidAI/RapidOCR/discussions/286)
- 非常感谢[zhsunlight](https://github.com/zhsunlight)关于参数化调用GPU推理的建议以及细致周到的测试。
- 非常感谢[lzh111222334](https://github.com/lzh111222334)修复python版本下rec前处理部分bug。
- 非常感谢[AutumnSun1996](https://github.com/AutumnSun1996)在[#42](https://github.com/RapidAI/RapidOCR/issues/42)中的建议。
-- 非常感谢[DeadWood8](https://github.com/DeadWood8)提供了[Nuitka打包rapidocr_web的操作文档和可执行exe](https://rapidai.github.io/RapidOCRDocs/install_usage/rapidocr_web/nuitka_package/)。
+- 非常感谢[DeadWood8](https://github.com/DeadWood8)提供了[Nuitka打包rapidocr_web的操作文档和可执行exe](https://rapidai.github.io/RapidOCRDocs/main/install_usage/rapidocr_web/nuitka_package/)。
- 非常感谢[Loovelj](https://github.com/Loovelj)指出对文本检测框排序时顺序问题，详情参见[issue 75](https://github.com/RapidAI/RapidOCR/issues/75)。
### 贡献者
@@ -111,7 +111,7 @@ Used by [link](https://github.com/RapidAI/RapidOCR/discussions/286)
