Training mode is not supported in this build.

[divisonofficer]

请提供下述完整信息以便快速定位问题
(Please provide the following information to quickly locate the problem)

• 系统环境/System Environment: Ubuntu 20.4 (WSL 2)
• 使用的是哪门语言的程序/Which programing language: Python3.8
• 所使用语言相关版本信息/Version: 0.6
• OnnxRuntime版本/OnnxRuntime Version: 1.8
• 使用rapidocr_onnxruntime版本/Use rapidocr_onnxruntime version: 1.3.16
• 可复现问题的demo和文件/Demo of reproducible problems: import LatexOcr, create instance of LatexOCR, run model

• 完整报错/Complete Error Message:
  onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Exception during initialization: /onnxruntime_src/onnxruntime/core/providers/cpu/nn/batch_norm.h:52 onnxruntime::BatchNorm::BatchNorm(const onnxruntime::OpKernelInfo&) [with T = float] !is_train_ was false. Training mode is not supported in this build.

• 可能的解决方案/Possible solutions:

How to disable Training mode?

[SWHL]

I tested the program in Google Colab, and do not meet the problem.
Can you try to test it on the Google Colab?
I want to ensure that the error can be reproduce.

For example code:

pip install rapid_latex_ocr

from rapid_latex_ocr import LatexOCR

model = LatexOCR()

img_path = "6.png"
with open(img_path, "rb") as f:
    data = f.read()

res, elapse = model(data)

print(res)
print(elapse)