Topit窗口置顶:解锁macOS多任务处理的终极效率密码
2025/12/27 5:21:17
from pathlib import Path from paddleocr import PPStructureV3 pipeline = PPStructureV3( use_doc_orientation_classify=True, # 禁用文档图像方向分类 use_doc_unwarping=True, # 禁用文本图像矫正 use_textline_orientation=True, # 禁用文本行方向分类 use_formula_recognition=True, # 禁用公式识别 use_seal_recognition=True, # 禁用印章文本识别 use_table_recognition=True, # 禁用表格识别 use_chart_recognition=True, # 禁用图表解析 # 使用轻量级模型 # text_detection_model_name="PP-OCRv5_mobile_det", # text_recognition_model_name="PP-OCRv5_mobile_rec", layout_detection_model_name="PP-DocLayout-S", text_detection_model_name="PP-OCRv5_server_det", # 文本检测模型名称 text_recognition_model_name="PP-OCRv5_server_rec", # 文本识别模型名称 text_detection_model_dir="./ckpt/PP-OCRv5_server_det", text_recognition_model_dir="./ckpt/PP-OCRv5_server_rec", ) # 配置文件保存到 `PP-StructureV3.yaml` 中 # pipeline.export_paddlex_config_to_yaml("PP-StructureV3.yaml") # For Image output = pipeline.predict( input=r"H:\SHANGFBANWORK\projecttest\PPOCRVersion\2025-07-28-13-12-48-01.jpg", ) # 可视化结果并保存 json 结果 for res in output: res.print() res.save_to_json(save_path="output") res.save_to_markdown(save_path="output") res.save_to_img(save_path="output")