Skip to content

PyTorch reimplementation of the paper "HyperMixer: An MLP-based Green AI Alternative to Transformers" [arXiv 2022].

License

Notifications You must be signed in to change notification settings

ChristophReich1996/HyperMixer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

HyperMixer: An MLP-based Green AI Alternative to Transformers

License: MIT

This is a very quick (and maybe wrong) PyTorch reimplementation of the HyperMixer.

Usage

import torch
from hyper_mixer import HyperMixerBlock

hyper_mixer_block = HyperMixerBlock(dim=32)
input = torch.rand(3, 256, 32)
output = hyper_mixer_block(input)
print(output.shape)

Reference

@article{Liu2021,
    title={{HyperMixer: An MLP-based Green AI Alternative to Transformers}},
    author={Mai, Florian and Pannatier, Arnaud and Fehr, Fabio and Chen, Haolin and Marelli, Francois 
    and Fleuret, Francois and Henderson, James},
    journal={arXiv preprint arXiv:2203.03691},
    year={2022}
}

About

PyTorch reimplementation of the paper "HyperMixer: An MLP-based Green AI Alternative to Transformers" [arXiv 2022].

Topics

Resources

License

Stars

Watchers

Forks

Languages