Convert offline handwritten mathematical expression to LaTeX sequence using bidirectionally trained transformer.

First, install dependencies

# clone project   
git clone https://github.com/Green-Wood/BTTR

# install project   
cd BTTR
conda create -y -n bttr python=3.7
conda activate bttr
conda install --yes -c pytorch pytorch=1.7.0 torchvision cudatoolkit=<your-cuda-version>
pip install -e .   

Next, navigate to any file and run it. It may take 6~7 hours to converge on 4 gpus using ddp.

# module folder
cd BTTR

# train bttr model using 4 gpus and ddp
python train.py --config config.yaml  

For single gpu user, you may change the config.yaml file to

gpus: 1
# gpus: 4
# accelerator: ddp

This project is setup as a package which means you can now easily import any file into any other file like so:

from bttr.datamodule import CROHMEDatamodule
from bttr import LitBTTR
from pytorch_lightning import Trainer

# model
model = LitBTTR()

# data
dm = CROHMEDatamodule(test_year=test_year)

# train
trainer = Trainer()
trainer.fit(model, datamodule=dm)

# test using the best model!
trainer.test(datamodule=dm)

Metrics used in validation is not accurate.

For more accurate metrics:

1. use test.py to generate result.zip
2. download and install crohmelib, lgeval, and tex2symlg tool.
3. convert tex file to symLg file using tex2symlg command
4. evaluate two folder using evaluate command

@article{zhao2021handwritten,
  title={Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer},
  author={Zhao, Wenqi and Gao, Liangcai and Yan, Zuoyu and Peng, Shuai and Du, Lin and Zhang, Ziyin},
  journal={arXiv preprint arXiv:2105.02412},
  year={2021}
}

@inproceedings{Zhao2021HandwrittenME,
  title={Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer},
  author={Wenqi Zhao and Liangcai Gao and Zuoyu Yan and Shuai Peng and Lin Du and Ziyin Zhang},
  booktitle={ICDAR},
  year={2021}
}