mirrors
/
mmsegmentation
mirror of https://github.com/open-mmlab/mmsegmentation.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
mmsegmentation/configs/deeplabv3
History
Jerry Jiarui XU e1f4f51dc6
[Feature] Add OS16 DeepLab (#154) 
* Add D16-MG124 models

* Use MMCV DepthSepConv

* add OHEM

* add warmup

* fixed test

* fixed test

* change to bs 16

* revert config

* add models
 		2020-09-29 20:00:48 +08:00
..
README.md [Feature] Add OS16 DeepLab (#154) 2020-09-29 20:00:48 +08:00
deeplabv3_r50-d8_480x480_40k_pascal_context.py Add Pascal Context to mmsegmentation (#133) 2020-09-22 14:56:13 +08:00
deeplabv3_r50-d8_480x480_80k_pascal_context.py Add Pascal Context to mmsegmentation (#133) 2020-09-22 14:56:13 +08:00
deeplabv3_r50-d8_512x512_20k_voc12aug.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r50-d8_512x512_40k_voc12aug.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r50-d8_512x512_80k_ade20k.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r50-d8_512x512_160k_ade20k.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r50-d8_512x1024_40k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r50-d8_512x1024_80k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r50-d8_769x769_40k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r50-d8_769x769_80k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r101-d8_480x480_40k_pascal_context.py Add Pascal Context to mmsegmentation (#133) 2020-09-22 14:56:13 +08:00
deeplabv3_r101-d8_480x480_80k_pascal_context.py Add Pascal Context to mmsegmentation (#133) 2020-09-22 14:56:13 +08:00
deeplabv3_r101-d8_512x512_20k_voc12aug.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r101-d8_512x512_40k_voc12aug.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r101-d8_512x512_80k_ade20k.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r101-d8_512x512_160k_ade20k.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r101-d8_512x1024_40k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r101-d8_512x1024_80k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r101-d8_769x769_40k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r101-d8_769x769_80k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes.py [Feature] Add OS16 DeepLab (#154) 2020-09-29 20:00:48 +08:00
deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes.py [Feature] Add OS16 DeepLab (#154) 2020-09-29 20:00:48 +08:00

README.md

Rethinking atrous convolution for semantic image segmentation

Introduction

@article{chen2017rethinking,
  title={Rethinking atrous convolution for semantic image segmentation},
  author={Chen, Liang-Chieh and Papandreou, George and Schroff, Florian and Adam, Hartwig},
  journal={arXiv preprint arXiv:1706.05587},
  year={2017}
}

Results and models

Note: D-8 here corresponding to the output stride 8 setting for DeepLab series.

Cityscapes

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) download
DeepLabV3 R-50-D8 512x1024 40000 6.1 2.57 79.09 80.45 model | log
DeepLabV3 R-101-D8 512x1024 40000 9.6 1.92 77.12 79.61 model | log
DeepLabV3 R-50-D8 769x769 40000 6.9 1.11 78.58 79.89 model | log
DeepLabV3 R-101-D8 769x769 40000 10.9 0.83 79.27 80.11 model | log
DeepLabV3 R-50-D8 512x1024 80000 - - 79.32 80.57 model | log
DeepLabV3 R-101-D8 512x1024 80000 - - 80.20 81.21 model | log
DeepLabV3 R-50-D8 769x769 80000 - - 79.89 81.06 model | log
DeepLabV3 R-101-D8 769x769 80000 - - 79.67 80.81 model | log
DeepLabV3 R-101-D16-MG124 512x1024 40000 4.7 - 6.96 76.71 78.63 model | log
DeepLabV3 R-101-D16-MG124 512x1024 80000 - - 78.36 79.84 model | log

ADE20K

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) download
DeepLabV3 R-50-D8 512x512 80000 8.9 14.76 42.42 43.28 model | log
DeepLabV3 R-101-D8 512x512 80000 12.4 10.14 44.08 45.19 model | log
DeepLabV3 R-50-D8 512x512 160000 - - 42.66 44.09 model | log
DeepLabV3 R-101-D8 512x512 160000 - - 45.00 46.66 model | log

Pascal VOC 2012 + Aug

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) download
DeepLabV3 R-50-D8 512x512 20000 6.1 13.88 76.17 77.42 model | log
DeepLabV3 R-101-D8 512x512 20000 9.6 9.81 78.70 79.95 model | log
DeepLabV3 R-50-D8 512x512 40000 - - 77.68 78.78 model | log
DeepLabV3 R-101-D8 512x512 40000 - - 77.92 79.18 model | log

Pascal Context

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) download
DeepLabV3 R-101-D8 480x480 40000 9.2 7.09 46.55 47.81 model | log
DeepLabV3 R-101-D8 480x480 80000 - - 46.42 47.53 model | log