🔎 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)

Paddle2ONNX 转换的模型，使用openvino加载模型报错 The value of scalar shape pattern should be equal to 1!

测试的转onnx模型，ocr的onnx是可以用openvino正常读取的，但是公式PP-FormulaNet_plus和版面PP-DocLayout转onnx后，onnxruntime推理正常，使用openvino读取报错 The value of scalar shape pattern should be equal to 1!

奇怪的是SLANet_plus这个模型在RapidTable很早之前是转好onnx的，使用openvino正常读取。但是我重新从.paddlex\official_models\SLANet_plus转为onnx，openvino同样会报错 The value of scalar shape pattern should be equal to 1!

🏃‍♂️ Environment (运行环境)

paddlex 3.1.3
openvino 2025.2.0

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

paddlex --paddle2onnx --paddle_model_dir C:\Users\huazhen\.paddlex\official_models\PP-FormulaNet_plus-S --onnx_model_dir C:\ocr\models\ppmodel\layout\PP-FormulaNet_plus-S --opset_version 11

from openvino.runtime import Core core = Core() model_onnx = core.read_model(test_path)