Skip to content

Awesome multilingual OCR and Document Parsing toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

License

Notifications You must be signed in to change notification settings

FahNos/pp_formula_to_onnx

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🚀 Exporting PP-FormulaNet_plus-M Model to ONNX

Step-by-step guide to converting PP-FormulaNet_plus-M from PaddlePaddle to ONNX, fixing the model, and running predictions.


📦 Installation

  1. Clone the repository

    git clone https://github.com/FahNos/pp_formula_to_onnx.git
    cd pp_formula_to_onnx
  2. Install dependencies

    pip install -r requirements_onnx.txt
  3. Download pre-trained model

    wget -P ./pretrained_model    https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-FormulaNet_plus-M_pretrained.pdparams

⚙️ Export the ONNX model

python ./tools/export_onnx.py --config ./configs/rec/PP-FormuaNet/PP-FormulaNet_plus-M_ONNX.yaml

🛠 Fix the ONNX model

python ./tools/fix_head_onnx.py

🔍 Run prediction

python ./tools/onnx_predict_pp_formualnet_plus_M.py --config ./configs/rec/PP-FormuaNet/PP-FormulaNet_plus-M_ONNX.yaml

📷 Input Image

Input Example


📊 Prediction Result

\zeta_{0}(\nu)=-\frac{\nu\varrho^{-2\nu}}{\pi}\int_{\mu}^{\infty}d\omega\int_{C_{+}}d z\frac{2z^{2}}{(z^{2}+\omega^{2})^{\nu+1}}\breve{\Psi}(\omega;z)e^{i\epsilon z}\quad,

⭐ Support

If this project helps you, please give it a ⭐ Star on GitHub!

About

Awesome multilingual OCR and Document Parsing toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 79.0%
  • C++ 12.6%
  • Shell 5.3%
  • Java 1.2%
  • Cuda 0.4%
  • CMake 0.4%
  • Other 1.1%