liuzhuang1024/sam

Semantic Graph Representation Learning for Handwritten Mathematical Expression Recognition (ICDAR 2023)

SAM

Semantic Graph Representation Learning for Handwritten Mathematical Expression Recognition (ICDAR 2023)

This is the official pytorch implementation of SAM[ICDAR'2023].

Zhuang Liu, Ye Yuan, Zhilong ji, Jingfeng Bai and Xiang Bai

Pipeline

Usage

You need config the config file and run train or inference after.

python train.py --config config_v2.yaml

Citation

@misc{liu2023semantic,
    title={Semantic Graph Representation Learning for Handwritten Mathematical Expression Recognition},
    author={Zhuang Liu and Ye Yuan and Zhilong Ji and Jingfeng Bai and Xiang Bai},
    year={2023},
    eprint={2308.10493},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

Recommendation

Some other excellent open-sourced HMER algorithms can be found here:

WAP[PR'2017] DWAP-TD[ICML'2020] BTTR[ICDAR'2021] ABM[AAAI'2022] SAN[CVPR'2022] CoMER[ECCV'2022] CAN[ECCV'2022]

sam's Issues

你好，能够提供一下权重模型

您好，能否提供一下代码中的权重文件（checkpoints/can-l2-context-word_2022-12-08-10-19_decoder-Decoder_v3/2014_can-l2-context-word_2022-12-08-10-19_decoder-Decoder_v3_WordRate-0.9037_ExpRate-0.5720_179.pth）

您好，能够提供训练模型，"checkpoints/can-l2-context-word_2022-12-08-10-19_decoder-Decoder_v3/2014_can-l2-context-word_2022-12-08-10-19_decoder-Decoder_v3_WordRate-0.9037_ExpRate-0.5720_179.pth"

您好，按照代码中的流程训练后，训练50轮word score为0.162 ExpRate为0.00，这是为什么呢