Transformer

Chasing Sparsity in Vision Transformers: An End-to-End Exploration

SViTE

[Preprint] “Chasing Sparsity in Vision Transformers: An End-to-End Exploration” by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

Extensive results on ImageNet with diverse ViT backbones validate the effectiveness of our proposals which obtain significantly reduced computational cost and almost unimpaired generalization. Perhaps most surprisingly, we find that the proposed sparse (co-)training can even improve the ViT accuracy rather than compromising it, making sparsity a tantalizing “free lunch”. For example, our sparsified DeiT-Small at (5%, 50%) sparsity for (data, architecture), improves 0.28% top-1 accuracy, and meanwhile enjoys 49.32% FLOPs and 4.40% running time savings.

Proposed Framework of SViTE

framework--1-

Implementations of SViTE

Set Environment

conda create -n vit python=3.6


pip install torch==1.7.1+cu101 torchvision==0.8.2+cu101 torchaudio==0.7.2 -f https://download.pytorch.org/whl/torch_stable.html


pip install tqdm


 


 




 


To finish reading, please visit source site