# 环境要求
lmdb==0.99
timm==0.4.12
easydict==1.9
pandas==1.2.4
jsonlines==2.0.0
tqdm==4.60.0
torchvision==0.9.1
numpy==1.20.2
torch==1.8.1
transformers==4.5.1
msgpack_numpy==0.4.7.1
msgpack_python==0.5.6
Pillow==8.3.1
PyYAML==5.4.1

pip install -r requirements.txt

cd evaluation/
bash test_xyb.sh

./data/imgs  # 放入图像
./data/jsonls # 放入图文对描述

@article{DBLP:journals/corr/abs-2103-06561,
  author    = {Yuqi Huo and
               Manli Zhang and
               Guangzhen Liu and
               Haoyu Lu and
               Yizhao Gao and
               Guoxing Yang and
               Jingyuan Wen and
               Heng Zhang and
               Baogui Xu and
               Weihao Zheng and
               Zongzheng Xi and
               Yueqian Yang and
               Anwen Hu and
               Jinming Zhao and
               Ruichen Li and
               Yida Zhao and
               Liang Zhang and
               Yuqing Song and
               Xin Hong and
               Wanqing Cui and
               Dan Yang Hou and
               Yingyan Li and
               Junyi Li and
               Peiyu Liu and
               Zheng Gong and
               Chuhao Jin and
               Yuchong Sun and
               Shizhe Chen and
               Zhiwu Lu and
               Zhicheng Dou and
               Qin Jin and
               Yanyan Lan and
               Wayne Xin Zhao and
               Ruihua Song and
               Ji{-}Rong Wen},
  title     = {WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training},
  journal   = {CoRR},
  volume    = {abs/2103.06561},
  year      = {2021},
  url       = {https://arxiv.org/abs/2103.06561},
  archivePrefix = {arXiv},
  eprint    = {2103.06561},
  timestamp = {Tue, 03 Aug 2021 12:35:30 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2103-06561.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}