History

sennnnn 2aa632ebe7 [Enhancement] Change readme style and Update metafiles. (#895 ) * [Enhancement] Change readme style and prepare for metafiles update. * Update apcnet github repo url. * add code snippet. * split code snippet & official repo. * update md2yml hook. * Update metafiles. * Add converted from attribute. * process conflict. * Put defualt variable value. * update bisenet v2 metafile. * checkout to ubuntu environment. * pop empty attribute & make task attribute list. * update readme style * update readme style * update metafiles Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>		2021-09-28 16:25:37 +08:00
..
README.md	[Enhancement] Change readme style and Update metafiles. (#895 )	2021-09-28 16:25:37 +08:00
dpt.yml	[Enhancement] Change readme style and Update metafiles. (#895 )	2021-09-28 16:25:37 +08:00
dpt_vit-b16_512x512_160k_ade20k.py	[Feature] add DPT head (#605 )	2021-08-30 16:53:05 +08:00

README.md

Vision Transformer for Dense Prediction

Introduction

Official Repo

Code Snippet

DPT (ArXiv'2021)

@article{dosoViTskiy2020,
  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
  author={DosoViTskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
  journal={arXiv preprint arXiv:2010.11929},
  year={2020}
}

@article{Ranftl2021,
  author    = {Ren\'{e} Ranftl and Alexey Bochkovskiy and Vladlen Koltun},
  title     = {Vision Transformers for Dense Prediction},
  journal   = {ArXiv preprint},
  year      = {2021},
}

Usage

To use other repositories' pre-trained models, it is necessary to convert keys.

We provide a script vit2mmseg.py in the tools directory to convert the key of models from timm to MMSegmentation style.

python tools/model_converters/vit2mmseg.py ${PRETRAIN_PATH} ${STORE_PATH}

E.g.

python tools/model_converters/vit2mmseg.py https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_p16_224-80ecf9dd.pth pretrain/jx_vit_base_p16_224-80ecf9dd.pth

This script convert model from PRETRAIN_PATH and store the converted model in STORE_PATH.

Results and models

ADE20K

Method	Backbone	Crop Size	Lr schd	Mem (GB)	Inf time (fps)	mIoU	mIoU(ms+flip)	config	download
DPT	ViT-B	512x512	160000	8.09	10.41	46.97	48.34	config	model \| log