mirrors
/
mmsegmentation
mirror of https://github.com/open-mmlab/mmsegmentation.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
mmsegmentation/configs/vit
History
谢昕辰 5245edb0a0 add configs for vit backbone plus decode_heads (#520) 
* add config

* add cityscapes config

* add default value to docstring

* fix lint

* add deit-s and deit-b

* add readme

* add eps at norm_cfg

* add drop_path_rate experiment

* add deit case at init_weight

* add upernet result

* update result and add upernet 160k config

* update upernet result and fix settings

* Update iters number

* update result and delete some configs

* fix import error

* fix drop_path_rate

* update result and restore config

* update benchmark result

* remove cityscapes exp

* remove neck

* neck exp

* add more configs

* fix init error

* fix ffn setting

* update result

* update results

* update result

* update results and fill table

* delete or rename configs

* fix link delimiter

* rename configs and fix link

* rename neck to mln
 		2021-07-01 23:00:39 +08:00
..
README.md add configs for vit backbone plus decode_heads (#520) 2021-07-01 23:00:39 +08:00
upernet_deit-b16_512x512_80k_ade20k.py add configs for vit backbone plus decode_heads (#520) 2021-07-01 23:00:39 +08:00
upernet_deit-b16_512x512_160k_ade20k.py add configs for vit backbone plus decode_heads (#520) 2021-07-01 23:00:39 +08:00
upernet_deit-b16_ln_mln_512x512_160k_ade20k.py add configs for vit backbone plus decode_heads (#520) 2021-07-01 23:00:39 +08:00
upernet_deit-b16_mln_512x512_160k_ade20k.py add configs for vit backbone plus decode_heads (#520) 2021-07-01 23:00:39 +08:00
upernet_deit-s16_512x512_80k_ade20k.py add configs for vit backbone plus decode_heads (#520) 2021-07-01 23:00:39 +08:00
upernet_deit-s16_512x512_160k_ade20k.py add configs for vit backbone plus decode_heads (#520) 2021-07-01 23:00:39 +08:00
upernet_deit-s16_ln_mln_512x512_160k_ade20k.py add configs for vit backbone plus decode_heads (#520) 2021-07-01 23:00:39 +08:00
upernet_deit-s16_mln_512x512_160k_ade20k.py add configs for vit backbone plus decode_heads (#520) 2021-07-01 23:00:39 +08:00
upernet_vit-b16_ln_mln_512x512_160k_ade20k.py add configs for vit backbone plus decode_heads (#520) 2021-07-01 23:00:39 +08:00
upernet_vit-b16_mln_512x512_80k_ade20k.py add configs for vit backbone plus decode_heads (#520) 2021-07-01 23:00:39 +08:00
upernet_vit-b16_mln_512x512_160k_ade20k.py add configs for vit backbone plus decode_heads (#520) 2021-07-01 23:00:39 +08:00

README.md

Vision Transformer

Introduction

@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}
}

Results and models

ADE20K

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) config download
UPerNet ViT-B + MLN 512x512 80000 9.20 6.94 47.71 49.51 config model | log
UPerNet ViT-B + MLN 512x512 160000 9.20 7.58 46.75 48.46 config model | log
UPerNet ViT-B + LN + MLN 512x512 160000 9.21 6.82 47.73 49.95 config model | log
UPerNet DeiT-S 512x512 80000 4.68 29.85 42.96 43.79 config model | log
UPerNet DeiT-S 512x512 160000 4.68 29.19 42.87 43.79 config model | log
UPerNet DeiT-S + MLN 512x512 160000 5.69 11.18 43.82 45.07 config model | log
UPerNet DeiT-S + LN + MLN 512x512 160000 5.69 12.39 43.52 45.01 config model | log
UPerNet DeiT-B 512x512 80000 7.75 9.69 45.24 46.73 config model | log
UPerNet DeiT-B 512x512 160000 7.75 10.39 45.36 47.16 config model | log
UPerNet DeiT-B + MLN 512x512 160000 9.21 7.78 45.46 47.16 config model | log
UPerNet DeiT-B + LN + MLN 512x512 160000 9.21 7.75 45.37 47.23 config model | log