AutoScaler

[PR 2026] AutoScaler: Self Scale Alignment for Handwritten Mathematical Expression Recognition

🛠️ Installation

• Clone this repo:

git clone https://github.com/SCUT-DLVCLab/AutoScaler.git
cd AutoScaler

• Create a virtual environment:

conda create -n autoscaler python=3.10 -y
conda activate autoscaler

• Install the required packages:

pip install -r requirements.txt

🔥 Training

• Download and process the dataset into the dataset folder.
• Generate the corresponding dictionary file dic.txt.
• Set the CUDA device in train.py and run 🚀:

cd AutoScaler
python train.py

🧠 Inference

• Set the checkpoint path in test.py and run:

python test.py

💐 Acknowledgements

This repo is modified based on BTTR. Special thanks for their contributions to the community.

🧰 Other Awesome Repos

• WAP

• DWAP-TD

• BTTR

• TSDNet

• ABM

• SAN

• CoMER

• CAN

• PosFormer

• TAMER

📜License

The code should be used and distributed under (CC BY-NC-ND 4.0) for non-commercial research purposes.

📧Contacts

If you have any questions, feel free to contact the author at wente_young@foxmail.com.