conda install pytorch==1.7.1 torchvision==0.8.2 torchaudio==0.7.2 cudatoolkit=11.0 -c pytorch
pip install transformers==4.8.1
pip install timm==0.4.9
conda install ruamel_yaml
pip install opencv-python
pip install --upgrade Pillow
pip install einops

python -m torch.distributed.launch --nproc_per_node=8 \
--use_env Pretrain.py \
--config ./configs/Pretrain.yaml \
--output_dir output/pretrain

# zero-shot coco 
python -m torch.distributed.launch --nproc_per_node=8 \
--use_env Retrieval.py \
--config ./configs/Retrieval_coco.yaml \
--output_dir output/pretrain_e30_Retrieval_coco_zeroshot \
--checkpoint output/pretrain/checkpoint_29.pth \
--evaluate

# fine-tune flickr
python -m torch.distributed.launch --nproc_per_node=8 \
--use_env Retrieval.py \
--config ./configs/Retrieval_flickr.yaml \
--output_dir output/pretrain_e30_Retrieval_flickr \
--checkpoint output/pretrain/checkpoint_29.pth

# fine-tune coco
python -m torch.distributed.launch --nproc_per_node=8 \
--use_env Retrieval.py \
--config ./configs/Retrieval_coco.yaml \
--output_dir output/pretrain_e30_Retrieval_coco \
--checkpoint output/pretrain/checkpoint_29.pth

# zero-shot flickr 
python -m torch.distributed.launch --nproc_per_node=8 \
--use_env Retrieval.py \
--config ./configs/Retrieval_flickr.yaml \
--output_dir output/pretrain_e30_Retrieval_flickr_zeroshot \
--checkpoint output/pretrain_e30_Retrieval_coco/checkpoint_best.pth \
--evaluate

python -m torch.distributed.launch --nproc_per_node=8 \
--use_env VQA.py \
--config ./configs/VQA.yaml \
--output_dir output/pretrain_e30_vqa \
--checkpoint output/pretrain/checkpoint_29.pth

python -m torch.distributed.launch --nproc_per_node=8 \
--use_env VE.py \
--config ./configs/VE.yaml \
--output_dir output/pretrain_e30_VE \
--checkpoint output/pretrain/checkpoint_29.pth

# pre-train nlvr
python -m torch.distributed.launch --nproc_per_node=8 \
--use_env Pretrain_nlvr.py \
--config ./configs/NLVR_pretrain.yaml \
--output_dir output/pretrain_e30_NLVR_pretrain \
--checkpoint output/pretrain/checkpoint_29.pth

# fine-tune nlvr
python -m torch.distributed.launch --nproc_per_node=8 \
--use_env NLVR.py \
--config ./configs/NLVR.yaml \
--output_dir output/pretrain_e30_NLVR \
--checkpoint output/pretrain_e30_NLVR_pretrain/checkpoint_00.pth

@article{yang2022vision,
  title={Vision-Language Pre-Training with Triple Contrastive Learning},
  author={Yang, Jinyu and Duan, Jiali and Tran, Son and Xu, Yi and Chanda, Sampath and Chen, Liqun and Zeng, Belinda and Chilimbi, Trishul and Huang, Junzhou},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  year={2022}
}