mirrors
/
mmsegmentation
mirror of https://github.com/open-mmlab/mmsegmentation.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
mmsegmentation/configs/deeplabv3plus
History
yamengxi a2738fd9be
Add Pascal Context to mmsegmentation (#133) 
* Add Pascal Context to mmsegmentation

* Add benchmark result to Pascal Context

* fix mmcv version

* fix code syntax

* fix code syntax again

* Update mmseg/models/segmentors/encoder_decoder.py

update hint

Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>

* update comment

* fix pascal context model path

* fix model path mistake again

* fix model path mistake again

* fix model path mistakes again

Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
 		2020-09-22 14:56:13 +08:00
..
README.md Add Pascal Context to mmsegmentation (#133) 2020-09-22 14:56:13 +08:00
deeplabv3plus_r50-d8_480x480_40k_pascal_context.py Add Pascal Context to mmsegmentation (#133) 2020-09-22 14:56:13 +08:00
deeplabv3plus_r50-d8_480x480_80k_pascal_context.py Add Pascal Context to mmsegmentation (#133) 2020-09-22 14:56:13 +08:00
deeplabv3plus_r50-d8_512x512_20k_voc12aug.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r50-d8_512x512_40k_voc12aug.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r50-d8_512x512_80k_ade20k.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r50-d8_512x512_160k_ade20k.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r50-d8_512x1024_40k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r50-d8_512x1024_80k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r50-d8_769x769_40k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r50-d8_769x769_80k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r101-d8_480x480_40k_pascal_context.py Add Pascal Context to mmsegmentation (#133) 2020-09-22 14:56:13 +08:00
deeplabv3plus_r101-d8_480x480_80k_pascal_context.py Add Pascal Context to mmsegmentation (#133) 2020-09-22 14:56:13 +08:00
deeplabv3plus_r101-d8_512x512_20k_voc12aug.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r101-d8_512x512_40k_voc12aug.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r101-d8_512x512_80k_ade20k.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r101-d8_512x512_160k_ade20k.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r101-d8_512x1024_40k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r101-d8_512x1024_80k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r101-d8_769x769_40k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
deeplabv3plus_r101-d8_769x769_80k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00

README.md

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Introduction

@inproceedings{deeplabv3plus2018,
  title={Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation},
  author={Liang-Chieh Chen and Yukun Zhu and George Papandreou and Florian Schroff and Hartwig Adam},
  booktitle={ECCV},
  year={2018}
}

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 7.5 3.94 79.61 81.01 model | log
DeepLabV3+ R-101-D8 512x1024 40000 11 2.60 80.21 81.82 model | log
DeepLabV3+ R-50-D8 769x769 40000 8.5 1.72 78.97 80.46 model | log
DeepLabV3+ R-101-D8 769x769 40000 12.5 1.15 79.46 80.50 model | log
DeepLabV3+ R-50-D8 512x1024 80000 - - 80.09 81.13 model | log
DeepLabV3+ R-101-D8 512x1024 80000 - - 80.97 82.03 model | log
DeepLabV3+ R-50-D8 769x769 80000 - - 79.83 81.48 model | log
DeepLabV3+ R-101-D8 769x769 80000 - - 80.98 82.18 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 10.6 21.01 42.72 43.75 model | log
DeepLabV3+ R-101-D8 512x512 80000 14.1 14.16 44.60 46.06 model | log
DeepLabV3+ R-50-D8 512x512 160000 - - 43.95 44.93 model | log
DeepLabV3+ R-101-D8 512x512 160000 - - 45.47 46.35 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 7.6 21 75.93 77.50 model | log
DeepLabV3+ R-101-D8 512x512 20000 11 13.88 77.22 78.59 model | log
DeepLabV3+ R-50-D8 512x512 40000 - - 76.81 77.57 model | log
DeepLabV3+ R-101-D8 512x512 40000 - - 78.62 79.53 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 - 9.09 47.30 48.47 model | log
DeepLabV3+ R-101-D8 480x480 80000 - - 47.23 48.26 model | log