This code is based on the publicly available code from the paper Masked Autoencoders Are Scalable Vision Learners:

@Article{MaskedAutoencoders2021,
  author  = {Kaiming He and Xinlei Chen and Saining Xie and Yanghao Li and Piotr Doll{\'a}r and Ross Girshick},
  journal = {arXiv:2111.06377},
  title   = {Masked Autoencoders Are Scalable Vision Learners},
  year    = {2021},
}

This repository is based on timm==0.3.2, for which a fix is needed to work with PyTorch 1.8.1+.

To fine-tune the model for ophthalmic disease classification, run:

bash scripts/opthalmic_loop.sh

To fine-tune the model for systemic disease classification, run:

bash scripts/chro_loop.sh

To perform cross-validation for diabetic retinopathy, run:

bash scripts/cross_data.sh

To pre-train ViT-Large (recommended default) with multi-node distributed training, run:

python main_pretrain_dl.py