rapidocr/python/README.md

使用步骤

1. 下载相应模型和用于显示的字体文件

   • 百度网盘 提取码：30jv | Google Drive

   • 下载之后放在models目录即可，最终models目录结构如下：

     models
       |-- ch_PP-OCRv2_det_infer.onnx
       |-- ch_ppocr_mobile_v2.0_cls_infer.onnx
       |-- ch_ppocr_mobile_v2.0_det_infer.onnx
       |-- ch_ppocr_server_v2.0_det_infer.onnx
       |-- ch_ppocr_server_v2.0_rec_infer.onnx
       |-- en_number_mobile_v2.0_rec_infer.onnx
       |-- japan_rec_crnn.onnx
       `-- msyh.ttc
     

2. 运行

   • 接口调用方式运行

     • 如果想要使用其他语言的识别模型，可以只对rec_model_path和keys_path作对应更改即可
     • !!!各个不同语言的推理代码区别只在于模型和字典文件!!!

       from rapid_ocr_api import TextSystem, visualize
       
       det_model_path = 'models/ch_ppocr_mobile_v2.0_det_infer.onnx'
       cls_model_path = 'models/ch_ppocr_mobile_v2.0_cls_infer.onnx'
       
       # 中英文识别
       rec_model_path = 'models/ch_ppocr_mobile_v2.0_rec_infer.onnx'
       keys_path = 'ch_ppocr_mobile_v2_rec/ppocr_keys_v1.txt'
       
       text_sys = TextSystem(det_model_path,
                           rec_model_path,
                           use_angle_cls=True,
                           cls_model_path=cls_model_path,
                           keys_path=keys_path)
       
       image_path = r'test_images/det_images/ch_en_num.jpg'
       dt_boxes, rec_res = text_sys(image_path)
       visualize(image_path, dt_boxes, rec_res)
       
       # 只有中英文和数字识别
       rec_model_path = 'models/en_number_mobile_v2.0_rec_infer.onnx'
       keys_path = 'en_number_ppocr_mobile_v2_rec/en_dict.txt'
       
       text_sys = TextSystem(det_model_path,
                           rec_model_path,
                           use_angle_cls=True,
                           cls_model_path=cls_model_path,
                           keys_path=keys_path)
       
       image_path = r'test_images/det_images/en_num.png'
       dt_boxes, rec_res = text_sys(image_path)
       visualize(image_path, dt_boxes, rec_res)
       
       # 日语识别
       rec_model_path = 'models/japan_rec_crnn.onnx'
       keys_path = 'japan_ppocr_mobile_v2_rec/japan_dict.txt'
       
       text_sys = TextSystem(det_model_path,
                           rec_model_path,
                           use_angle_cls=True,
                           cls_model_path=cls_model_path,
                           keys_path=keys_path)
       
       image_path = r'test_images/det_images/japan.png'
       dt_boxes, rec_res = text_sys(image_path)
       visualize(image_path, dt_boxes, rec_res)
       

   • 命令行运行

     $ bash test_demo.sh
     

相关调节参数

参数名称	作用	建议取值范围	默认值	代码位置
box_thresh	文本检测所得框是否保留的阈值，值越大，召回率越低	[0, 1]	0.5	text_detect.py
unclip_ratio	控制文本检测框的大小，值越大，检测框整体越大	[1.6, 2.0]	1.6	text_detect.py
text_score	文本识别结果置信度，值越大，把握越大	[0, 1]	0.5	rapidOCR.py

onnxruntime-gpu版推理配置

1. ONNXRuntime-gpu需要严格按照与cuda、cudnn版本对应来安装，具体参考文档, 这一步关乎后面是否可以成功调用GPU
2. 推理代码中，加载onnx模型部分，用以下对应语言代码替换即可,详细参见：官方教程
   • python版本

     import onnxruntime as ort
     
     model_path = '<path to model>'
     
     providers = [
        ('CUDAExecutionProvider', {
           'device_id': 0,
           'arena_extend_strategy': 'kNextPowerOfTwo',
           'gpu_mem_limit': 2 * 1024 * 1024 * 1024,
           'cudnn_conv_algo_search': 'EXHAUSTIVE',
           'do_copy_in_default_stream': True,
        }),
        'CPUExecutionProvider',
     ]
     
     session = ort.InferenceSession(model_path, providers=providers)
     

   • C/C++版本

     OrtSessionOptions* session_options = /* ... */;
     
     OrtCUDAProviderOptions options;
     options.device_id = 0;
     options.arena_extend_strategy = 0;
     options.gpu_mem_limit = 2 * 1024 * 1024 * 1024;
     options.cudnn_conv_algo_search = OrtCudnnConvAlgoSearch::EXHAUSTIVE;
     options.do_copy_in_default_stream = 1;
     
     SessionOptionsAppendExecutionProvider_CUDA(session_options, &options);