Skip to content

Implementation of Convolutional enhanced image Transformer

License

Notifications You must be signed in to change notification settings

rishikksh20/CeiT-pytorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CeiT : Convolutional enhanced image Transformer

This is an unofficial PyTorch implementation of Incorporating Convolution Designs into Visual Transformers .

Training :

python train.py -c configs/default.yaml --name "name_of_exp"

Usage :

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]

Note :

  • LCA might not be properly implemented.

Citation :

@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}
}

Acknowledgement :