37 lines
1.2 KiB
Python
37 lines
1.2 KiB
Python
import logging
|
||
|
||
from Util.GGB.GGB_1_CUT import yoloCut
|
||
from Util.GGB.GGB_2_OCR import pix2text_ocr
|
||
from Util.GGB.GGB_3_GLM import batch_glm
|
||
from Util.GGB.GGB_4_LLM import generate_ggb
|
||
|
||
# 更详细地控制日志输出
|
||
logger = logging.getLogger('GGB')
|
||
logger.setLevel(logging.INFO)
|
||
handler = logging.StreamHandler()
|
||
handler.setFormatter(logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s'))
|
||
logger.addHandler(handler)
|
||
|
||
if __name__ == '__main__':
|
||
# 图片路径
|
||
image_path = '../../Test/img10.jpg'
|
||
|
||
# 步骤1：调用yoloCut函数
|
||
output_dir, processed_image_path, img_list = yoloCut(image_path)
|
||
|
||
# 步骤2：调用pix2text_ocr函数
|
||
ocr_result = pix2text_ocr(output_dir, processed_image_path)
|
||
logger.info(f"成功生成文字+公式OCR文件: {ocr_result}")
|
||
|
||
# 步骤3：调用QVQ解析图片
|
||
qvq_result = batch_glm(output_dir, img_list)
|
||
logger.info(f"成功生成图形解析文件: {qvq_result}")
|
||
|
||
# 步骤4：生成GGB指令
|
||
ggb = generate_ggb(ocr_result, qvq_result, output_dir)
|
||
logger.info(f"成功生成GGB文件: {ggb}")
|
||
|
||
# 步骤5：输出GGB指令集
|
||
with open(ggb, 'r', encoding='utf-8') as f:
|
||
print(f.read())
|