Segmentation fault

bug描述 Describe the Bug

from paddleocr import TextRecognition model = TextRecognition(model_dir="/home/code/handwriting/PP-OCRv6_medium_rec",device="cpu") output = model.predict(input=image, batch_size=1) for res in output: res.print() #########

报错C++ Traceback (most recent call last):

No stack trace in paddle, may be caused by external reasons.

---

Error Message Summary:

FatalError: Segmentation fault is detected by the operating system. [TimeInfo: *** Aborted at 1782205367 (unix time) try "date -d @1782205367" if you are using GNU date ***] [SignalInfo: *** SIGSEGV (@0x0) received by PID 105166 (TID 0xffff3fe1f1a0) from PID 0 ***]

Segmentation fault (core dumped)

其他补充信息 Additional Supplementary Information

CPU是鲲鹏920，系统是麒麟V11。 opencv-python-headless 4.13.0.92 paddleocr 3.7.0 paddlepaddle 3.2.2 paddlex 3.7.1 有资料显示在新版本已经修复了这个问题，所以基本升级到了最新，但是依然没有效果。 opencv-python-headless是我修改底层代码后充当cv2库的，在x86服务器上运行无问题。 根据网络资料建议，把PP-OCRv6_medium_rec换成小一些的PP-OCRv6_small_rec模型，无效果。 根据网络资料建议，图片缩放，最长边不超过（960,840,720），无效果。