diff --git a/PPOCRLabel/README.md b/PPOCRLabel/README.md index 089a63fd55bb8c127104e7c404852ba52c3ac88c..9c483e1feff5a07467f7aa90343391888004bce7 100644 --- a/PPOCRLabel/README.md +++ b/PPOCRLabel/README.md @@ -105,9 +105,9 @@ python PPOCRLabel.py --kie True # [KIE mode] for [detection + recognition + keyw #### 1.2.3 Build and Install the Whl Package Locally Compile and install a new whl package, where 1.0.2 is the version number, you can specify the new version in 'setup.py'. ```bash -cd PaddleOCR/PPOCRLabel +cd ./PPOCRLabel python3 setup.py bdist_wheel -pip3 install dist/PPOCRLabel-1.0.2-py2.py3-none-any.whl +pip3 install dist/PPOCRLabel-2.1.2-py2.py3-none-any.whl ``` diff --git a/PPOCRLabel/README_ch.md b/PPOCRLabel/README_ch.md index 767102fb1aaa696667b8e584ba8d2d1a17faa82e..afe1a08ff9c5445b2643b9453985951fcb7a90f5 100644 --- a/PPOCRLabel/README_ch.md +++ b/PPOCRLabel/README_ch.md @@ -104,9 +104,9 @@ python PPOCRLabel.py --lang ch 编译与安装新的whl包,其中1.0.2为版本号,可在 `setup.py` 中指定新版本。 ```bash -cd PaddleOCR/PPOCRLabel +cd ./PPOCRLabel python3 setup.py bdist_wheel -pip3 install dist/PPOCRLabel-1.0.2-py2.py3-none-any.whl -i https://mirror.baidu.com/pypi/simple +pip3 install dist/PPOCRLabel-2.1.2-py2.py3-none-any.whl -i https://mirror.baidu.com/pypi/simple ``` diff --git a/PPOCRLabel/setup.py b/PPOCRLabel/setup.py index 1750f84b8259a237fb6bb1b5eb9dc33e29441bc1..a112df544ee385ba3dc87ffac3e15a9dc390c4db 100644 --- a/PPOCRLabel/setup.py +++ b/PPOCRLabel/setup.py @@ -33,7 +33,7 @@ setup( package_dir={'PPOCRLabel': ''}, include_package_data=True, entry_points={"console_scripts": ["PPOCRLabel= PPOCRLabel.PPOCRLabel:main"]}, - version='2.1.1', + version='2.1.2', install_requires=requirements, license='Apache License 2.0', description='PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field, with built-in PPOCR model to automatically detect and re-recognize data. It is written in python3 and pyqt5, supporting rectangular box annotation and four-point annotation modes. Annotations can be directly used for the training of PPOCR detection and recognition models', diff --git a/ppstructure/pdf2word/README.md b/ppstructure/pdf2word/README.md index 564df4063e101e028afbea5c3acab8946196d31d..45869124ff6bdb8f4301f04d58e6f6a6339e74dc 100644 --- a/ppstructure/pdf2word/README.md +++ b/ppstructure/pdf2word/README.md @@ -1,6 +1,6 @@ # PDF2WORD -PDF2WORD是PaddleOCR社区开发者[whjdark](https://github.com/whjdark) 基于PP-Structure智能文档分析模型实现的PDF转换Word应用程序,提供可直接安装的exe,方便windows用户运行 +PDF2Word是PaddleOCR社区开发者 [whjdark](https://github.com/whjdark) 基于PP-StructureV2版面分析与恢复模型实现的PDF转换Word应用程序,提供可直接安装的exe应用程序,**方便Windows用户免环境配置运行** ## 1.使用 @@ -12,12 +12,30 @@ PDF2WORD是PaddleOCR社区开发者[whjdark](https://github.com/whjdark) 基于P ### 脚本运行 -首次运行需要将切换路径到 `/ppstructure/pdf2word` ,然后运行代码 +3. 打开结果:点击`显示结果`,即可打开转换完成后的文件夹 + +> 注意: +> +> - 初次安装程序根据不同设备需要等待1-2分钟不等 +> - 使用Office与WPS打开的Word结果会出现不同,推荐以Office为准 +> - 本程序使用 [QPT](https://github.com/QPT-Family/QPT) 进行应用程序打包,感谢 [GT-ZhangAcer](https://github.com/GT-ZhangAcer) 对打包过程的支持 +> - 应用程序不支持盗版Windows系统,若在安装过程中出现报错或缺少依赖,推荐直接使用 `paddleocr` whl包应用PDF2Word功能,详情可查看[链接](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/ppstructure/docs/quickstart.md) + +### 脚本启动界面 + +首次运行需要将切换路径到PaddleOCR文件目录 ,然后运行代码 ``` +cd ./ppstructure/pdf2word python pdf2word.py ``` +### PaddleOCR whl包 + +针对Linux、Mac用户或已经拥有Python环境的用户,**推荐安装 `paddleocr` whl包直接应用PDF2Word功能**,详情可查看[链接](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/ppstructure/docs/quickstart.md) + + + ## 2.软件下载 如需获取已打包程序,可以扫描下方二维码,关注公众号填写问卷后,加入PaddleOCR官方交流群免费获取20G OCR学习大礼包,内含OCR场景应用集合(包含数码管、液晶屏、车牌、高精度SVTR模型等7个垂类模型)、《动手学OCR》电子书、课程回放视频、前沿论文等重磅资料 @@ -26,3 +44,6 @@ python pdf2word.py +## 3.版本说明 + +v0.2版:新加入PDF解析功能,仅提供full版本,打包了所有依赖包与模型文件,尽可能避免安装失败问题。若仍然安装失败,推荐使用 `paddleocr` whl包 diff --git a/ppstructure/pdf2word/pdf2word.py b/ppstructure/pdf2word/pdf2word.py index a287fb248c3c947157401109a2d7df120dfbeda5..735fa5350a8f4f3bdc4ac62f3772083705ea3589 100644 --- a/ppstructure/pdf2word/pdf2word.py +++ b/ppstructure/pdf2word/pdf2word.py @@ -213,8 +213,8 @@ class Worker(QThread): class APP_Image2Doc(QWidget): def __init__(self): super().__init__() - self.setFixedHeight(100) - self.setFixedWidth(420) + # self.setFixedHeight(100) + # self.setFixedWidth(520) # settings self.imagePaths = [] @@ -481,7 +481,7 @@ class APP_Image2Doc(QWidget): def handleThreadException(self, message): self._thread.quit() - QMessageBox.information(self, message) + QMessageBox.information(self, 'Error', message) def main():