This is an unofficial PyTorch implementation of Incorporating Convolution Designs into Visual Transformers .
python train.py -c configs/default.yaml --name "name_of_exp"
import torch
from ceit import CeiT
img = torch.ones([1, 3, 224, 224])
model = CeiT(image_size = 224, patch_size = 4, num_classes = 100)
out = model(img)
print("Shape of out :", out.shape) # [B, num_classes]
model = CeiT(image_size = 224, patch_size = 4, num_classes = 100, with_lca = True)
out = model(img)
print("Shape of out :", out.shape) # [B, num_classes]- LCA might not be properly implemented.
@misc{yuan2021incorporating,
title={Incorporating Convolution Designs into Visual Transformers},
author={Kun Yuan and Shaopeng Guo and Ziwei Liu and Aojun Zhou and Fengwei Yu and Wei Wu},
year={2021},
eprint={2103.11816},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
- Base ViT code is borrowed from @lucidrains repo : https://github.com/lucidrains/vit-pytorch
- Training and dataloader code is borrowed from @jeonsworld repo : https://github.com/jeonsworld/ViT-pytorch
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent