python版本下的测试结果跟c++下面的测试结果有差异

[enfuliu]

🔎 Search before asking

• I have searched the PaddleOCR Docs and found no similar bug report.
• I have searched the PaddleOCR Issues and found no similar bug report.
• I have searched the PaddleOCR Discussions and found no similar bug report.

🐛 Bug (问题描述)

您好！我用ppocrv5的时候，发现python的结果是对的，但是转到了onnx 在c++下的结果，偶尔会有一两个字错误的，请问这个是什么原因？

🏃‍♂️ Environment (运行环境)

‘’‘
windows 11
cuda 11.3
‘’’

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

‘’‘
from paddleocr import TextRecognition

model = TextRecognition(model_name="PP-OCRv5_server_rec",model_dir="./official_models/PP-OCRv5_server_rec")

output = model.predict(input="8.jpg)

‘’’