Skip to content

xingxing-123/BurgerFormer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ee3e107 · Nov 6, 2022

History

10 Commits
Jul 19, 2022
Jul 19, 2022
Nov 3, 2022
Nov 3, 2022
Nov 3, 2022
Nov 3, 2022
Jul 19, 2022
Nov 3, 2022
Jul 19, 2022
Nov 3, 2022
Nov 3, 2022
Jul 19, 2022
Jul 19, 2022
Nov 3, 2022
Jul 19, 2022
Nov 3, 2022
Nov 6, 2022
Jul 19, 2022
Jul 19, 2022
Nov 3, 2022

Repository files navigation

Searching for BurgerFormer with Micro-Meso-Macro Space Design (ICML 2022)

This is an official pytorch implementation for "Searching for BurgerFormer with Micro-Meso-Macro Space Design". BurgerFormer-img1 BurgerFormer-img2

Requirements

  • PyTorch 1.8.0
  • timm 0.4.12

BurgerFormer Models

Pre-trained checkpoints are released google drive/baiduyun. Place them in the .checkpoints/ folder.

Note: access code for baiduyun is gvfl.

model FLOPs/G Params/M ImageNet Top1/%
BurgerFormer-tiny 1.0 10 78.0
BurgerFormer-small 2.1 14 80.4
BurgerFormer-base 3.9 26 82.7
BurgerFormer-large 6.5 36 83.0

Validation

To evaluate a pre-trained BurgerFormer model on ImageNet, run:

bash script/test.sh

Train

To retrain a BurgerFormer model on ImageNet, run:

bash script/train.sh

Search

  1. Split ImageNet training dataset to get sub-train & sub-val
bash script/imagenet_build.sh
  1. Supernet Training (8 V100 32G)
bash script/train_supernet.sh
  1. Evolution Search
bash script/search_evo.sh

Then the searched "myburger" will exist in arch.py

Citation

Please cite our paper if you find anything helpful.

@InProceedings{yang2022burgerformer,
  title={Searching for BurgerFormer with Micro-Meso-Macro Space Design},
  author={Yang, Longxing and Hu, Yu and Lu, Shun and Sun, Zihao and Mei, Jilin and Han, Yinhe and Li, Xiaowei},
  booktitle={ICML},
  year={2022}
}

Acknowledgment

This code is heavily based on poolformer, ViT-ResNAS, pytorch-image-models, mmdetection. Great thanks to their contributions.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published