PP-OCRv5_server_det模块运行报错

### 🔎 Search before asking

- [x] I have searched the PaddleOCR [Docs](https://paddlepaddle.github.io/PaddleOCR/) and found no similar bug report.
- [x] I have searched the PaddleOCR [Issues](https://github.com/PaddlePaddle/PaddleOCR/issues) and found no similar bug report.
- [x] I have searched the PaddleOCR [Discussions](https://github.com/PaddlePaddle/PaddleOCR/discussions) and found no similar bug report.

### 🐛 Bug (问题描述)

使用text_detection_model_name="PP-OCRv5_server_det"时，运行报错，try catch抓不到具体的错误，只显示**bus error**
图片尺寸：3024 × 4032
运行时提示：
Resized image size (4032x3024) exceeds max_side_limit of 4000. Resizing to fit within limit.
但是模块切换为text_detection_model_name="PP-OCRv5_mobile_det",执行一切正常,也会有
Resized image size (4032x3024) exceeds max_side_limit of 4000. Resizing to fit within limit的提示，但是不会报错
经测试，如果python版本在3.8执行也不会报错，高于3.8就不行

### 🏃‍♂️ Environment (运行环境)

```bash
OS:macOS-15.5
Environment:miniconda
Python:3.12.11 **(实际测试，只要高于3.8以上的环境都会如此)**
paddleocr                 3.0.1                    pypi_0    pypi
paddlepaddle              3.0.0                    pypi_0    pypi
paddlex                   3.0.1                    pypi_0    pypi
Install: pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple --use-pep517
RAM: 32GB
CPU: Apple M1max
CUDA: None
```

### 🌰 Minimal Reproducible Example (最小可复现问题的Demo)

```python
from paddleocr import PaddleOCR

ocr = PaddleOCR(
    text_detection_model_name="PP-OCRv5_server_det",
    text_recognition_model_name="PP-OCRv5_server_rec",
    use_doc_orientation_classify=False,
    use_doc_unwarping=False,
    use_textline_orientation=False,
    enable_mkldnn=False)
try:    
    result = ocr.predict("./output/step2/test.jpeg")
except Exception as e:
    print(e)
for res in result:
    res.print()
    res.save_to_img("output")
    res.save_to_json("output")
```

GVP PaddlePaddle/PaddleOCR

内容风险标识

评论 (0)

GVPPaddlePaddle/PaddleOCR

内容风险标识