curl --output gpt2-pytorch_model.bin https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-pytorch_model.bin

conda env create -f environment.yml
conda activate visualgpt

python -m spacy download en

python train_visualGPT.py --batch_size 50 --head 12 --features_path coco_detections.hdf5 --annotation_folder annotations --lr 1e-4 --gpt_model_type gpt --random_seed 42 --log_file logs/log --exp_name experiment_log --lr 1e-4 --decoder_layer 12 --optimizer_type adamw  --gradient_accumulation_steps 2 --train_percentage 0.001 --split_train_data

@article{chen2021visualgpt,
  title={VisualGPT: Data-efficient Image Captioning by Balancing Visual Input and Linguistic Knowledge from Pretraining},
  author={Chen, Jun and Guo, Han and Yi, Kai and Li, Boyang and Elhoseiny, Mohamed},
  journal={arXiv preprint arXiv:2102.10407},
  year={2021}
}

@article{chen2021visualgpt,
  title={VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning},
  author={Chen, Jun and Guo, Han and Yi, Kai and Li, Boyang and Elhoseiny, Mohamed},
  journal={arXiv preprint arXiv:2102.10407},
  year={2021}
}