Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
liangsuyin 2f9921dfd1 | 1 year ago | |
---|---|---|
__pycache__ | 1 year ago | |
checkpoints | 1 year ago | |
data | 1 year ago | |
infer | 1 year ago | |
logs | 1 year ago | |
models | 1 year ago | |
.gitignore | 1 year ago | |
14.yaml | 1 year ago | |
README.md | 1 year ago | |
bad_case.json | 1 year ago | |
config.py | 1 year ago | |
config.yaml | 1 year ago | |
counting_utils.py | 1 year ago | |
dataset.py | 1 year ago | |
image.py | 1 year ago | |
inference.py | 1 year ago | |
language_model_eval.csv | 1 year ago | |
language_model_train.csv | 1 year ago | |
overview.png | 1 year ago | |
read_labels.py | 1 year ago | |
requirement.txt | 1 year ago | |
train.py | 1 year ago | |
train_84.jpg | 1 year ago | |
training.py | 1 year ago | |
utils.py | 1 year ago |
This is the official pytorch implementation of SAN (CVPR'2022).
python==3.8.5
numpy==1.22.2
opencv-python==4.5.5.62
PyYAML==6.0
tensorboardX==2.5
torch==1.6.0+cu101
torchvision==0.7.0+cu101
tqdm==4.64.0
python train.py --config path_to_config_yaml
python inference.py --config path_to_config_yaml --image_path path_to_image_folder --label_path path_to_label_folder
Example:
python inference.py --config 14.yaml --image_path data/14_test_images --label_path data/test_caption.txt
CROHME:
Download the dataset from: https://github.com/JianshuZhang/WAP/tree/master/data
HME100K
Download the dataset from the official website: https://ai.100tal.com/dataset
If you find this dataset helpful for your research, please cite the following paper:
@inproceedings{yuan2022syntax,
title={Syntax-Aware Network for Handwritten Mathematical Expression Recognition},
author={Yuan, Ye and Liu, Xiao and Dikubab, Wondimu and Liu, Hui and Ji, Zhilong and Wu, Zhongqin and Bai, Xiang},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={4553--4562},
year={2022}
}
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》