VLGrammar: Grounded Grammar Induction of Vision and Language

conda create -n vlgrammar python=3.7 pytorch=1.7.1 torchvision -c pytorch
conda activate vlgrammar

pip install -r requirements.txt

git clone --branch infer_pos_tag https://github.com/zhaoyanpeng/pytorch-struct.git
cd pytorch-struct
pip install -e 

cd SCAN
python simclr.py --config_env configs/env.yml --config_exp configs/pretext/simclr_partit_chair.yml
python scan.py --config_env configs/env.yml --config_exp configs/scan/scan_partit_chair.yml

cd VLGrammr
python train.py or python train.py --type chair

@misc{hong2021vlgrammar,
      title={VLGrammar: Grounded Grammar Induction of Vision and Language}, 
      author={Yining Hong and Qing Li and Song-Chun Zhu and Siyuan Huang},
      year={2021},
      journal={ICCV},
}