RapidAI/paddleocr_convert：PaddleOCR中模型快速转换为ONNX格式

paddleocr_convert

• 本仓库主要是针对性地将PaddleOCR中推理模型转换为ONNX格式。
• 注意：
  • 输入：推理模型的url或者本地tar路径
  • 输出：转换后的ONNX模型
  • 如果是识别模型，需要提供对应字典的原始txt路径（打开github中txt文件，点击右上角raw之后的路径），用来将字典写入到onnx模型中
  • ！！！需要搭配RapidOCR中相关推理代码使用

使用步骤

1. 安装paddleocr_convert

   pip install paddleocr_convert
   

2. 命令行使用

   • 用法:

     $ paddleocr_convert -h
     usage: paddleocr_convert [-h] [-p MODEL_PATH] [-o SAVE_DIR]
                             [-txt_path TXT_PATH]
     
     optional arguments:
     -h, --help            show this help message and exit
     -p MODEL_PATH, --model_path MODEL_PATH
                             The inference model url or local path of paddleocr.
                             e.g. https://paddleocr.bj.bcebos.com/PP-
                             OCRv3/chinese/ch_PP-OCRv3_det_infer.tar or
                             models/ch_PP-OCRv3_det_infer.tar
     -o SAVE_DIR, --save_dir SAVE_DIR
                             The directory of saving the model.
     -txt_path TXT_PATH, --txt_path TXT_PATH
                             The raw txt url or local txt path, if the model is
                             recognition model.
     

   • 示例:

     # online
     $ paddleocr_convert -p https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar \
                         -o models
     
     $ paddleocr_convert -p https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar \
                         -o models \
                         -txt_path https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.6/ppocr/utils/ppocr_keys_v1.txt
     
     # offline
     $ paddleocr_convert -p models/ch_PP-OCRv3_det_infer.tar \
                         -o models
     
     $ paddleocr_convert -p models/ch_PP-OCRv3_rec_infer.tar \
                         -o models \
                         -txt_path models/ppocr_keys_v1.txt
     

3. 脚本使用

   from paddleocr_convert import PaddleOCRModelConvert
   
   converter = PaddleOCRModelConvert()
   
   save_dir = 'models'
   
   # online
   url = 'https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar'
   txt_url = 'https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.6/ppocr/utils/ppocr_keys_v1.txt'
   
   converter(url, save_dir, txt_path=txt_url)
   
   # offline
   model_path = 'models/ch_PP-OCRv3_rec_infer.tar'
   txt_path = 'models/ppocr_keys_v1.txt'
   converter(model_path, save_dir, txt_path=txt_path)
   

4. 使用模型方法：

   • 假设要用日文识别模型，且已经转好，路径为local/models/japan.onnx
   1. 安装rapidocr_onnxruntime库

      pip install rapidocr_onnxruntime
      

   2. 脚本使用

      from rapidocr_onnxruntime import RapidOCR
      
      model_path = 'local/models/japan.onnx'
      engine = RapidOCR(rec_model_path=model_path)
      
      img = '1.jpg'
      result, elapse = engine(img)
      

   3. 命令行使用

      $ rapidocr_onnxruntime -img 1.jpg --rec_model_path local/models/japan.onnx
      

更新日志