PaddleX/zhch/test_paddleocr_vl_client.py

from paddlex import create_pipeline
import time
from pathlib import Path

# input_path = "./sample_data/300674-母公司现金流量表-扫描.png"
input_path = "/home/ubuntu/zhch/data/至远彩色印刷工业有限公司/2023年度报告母公司.img/2023年度报告母公司_page_006.png"

pipeline_path = "./my_config/PaddleOCR-VL-Client.yaml"
pipeline_name = Path(pipeline_path).stem
output_path = Path(f"./sample_data/single_pipeline_output/{pipeline_name}/")

pipeline = create_pipeline(pipeline=pipeline_path)

# For Image
output = pipeline.predict(
    input=input_path,
    useLayoutDetection=True,
    useDocOrientationClassify=False, # 开启文档方向分类
    useDocUnwarping=False, # 开启文档去畸变
)

# 可视化结果并保存 json 结果
for res in output:
    res.print() 
    # res.save_to_json(save_path="sample_data/output") 
    # res.save_to_markdown(save_path="sample_data/output") 
    output_path.mkdir(parents=True, exist_ok=True)
    res.save_all(save_path=output_path.as_posix())  # 保存所有结果到指定路径