mmsegmentation/configs/nonlocal_net
sennnnn d35fbbdb47
[Enhancement] Add Dev tools to boost develop (#798)
* Modify default work dir when training.

* Refactor gather_models.py.

* Add train and test matching list.

* Regression benchmark list.

* lower readme name to upper readme name.

* Add url check tool and model inference test tool.

* Modify tool name.

* Support duplicate mode of log json url check.

* Add regression benchmark evaluation automatic tool.

* Add train script generator.

* Only Support script running.

* Add evaluation results gather.

* Add exec Authority.

* Automatically make checkpoint root folder.

* Modify gather results save path.

* Coarse-grained train results gather tool.

* Complete benchmark train script.

* Make some little modifications.

* Fix checkpoint urls.

* Fix unet checkpoint urls.

* Fix fast scnn & fcn checkpoint url.

* Fix fast scnn checkpoint urls.

* Fix fast scnn url.

* Add differential results calculation.

* Add differential results of regression benchmark train results.

* Add an extra argument to select model.

* Update nonlocal_net & hrnet checkpoint url.

* Fix checkpoint url of hrnet and Fix some tta evaluation results and modify gather models tool.

* Modify fast scnn checkpoint url.

* Resolve new comments.

* Fix url check status code bug.

* Resolve some comments.

* Modify train scripts generator.

* Modify work_dir of regression benchmark results.

* model gather tool modification.
2021-09-02 09:44:51 -07:00
..
README.md [Enhancement] Add Dev tools to boost develop (#798) 2021-09-02 09:44:51 -07:00
nonlocal_net.yml [Enhancement] Add Dev tools to boost develop (#798) 2021-09-02 09:44:51 -07:00
nonlocal_r50-d8_512x512_20k_voc12aug.py init commit 2020-07-10 02:39:01 +08:00
nonlocal_r50-d8_512x512_40k_voc12aug.py init commit 2020-07-10 02:39:01 +08:00
nonlocal_r50-d8_512x512_80k_ade20k.py init commit 2020-07-10 02:39:01 +08:00
nonlocal_r50-d8_512x512_160k_ade20k.py init commit 2020-07-10 02:39:01 +08:00
nonlocal_r50-d8_512x1024_40k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
nonlocal_r50-d8_512x1024_80k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
nonlocal_r50-d8_769x769_40k_cityscapes.py [Improvement] Move train_cfg/test_cfg inside model (#341) 2021-01-19 17:06:23 -08:00
nonlocal_r50-d8_769x769_80k_cityscapes.py [Improvement] Move train_cfg/test_cfg inside model (#341) 2021-01-19 17:06:23 -08:00
nonlocal_r101-d8_512x512_20k_voc12aug.py init commit 2020-07-10 02:39:01 +08:00
nonlocal_r101-d8_512x512_40k_voc12aug.py init commit 2020-07-10 02:39:01 +08:00
nonlocal_r101-d8_512x512_80k_ade20k.py init commit 2020-07-10 02:39:01 +08:00
nonlocal_r101-d8_512x512_160k_ade20k.py init commit 2020-07-10 02:39:01 +08:00
nonlocal_r101-d8_512x1024_40k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
nonlocal_r101-d8_512x1024_80k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
nonlocal_r101-d8_769x769_40k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00
nonlocal_r101-d8_769x769_80k_cityscapes.py init commit 2020-07-10 02:39:01 +08:00

README.md

Non-local Neural Networks

Introduction

@inproceedings{wang2018non,
  title={Non-local neural networks},
  author={Wang, Xiaolong and Girshick, Ross and Gupta, Abhinav and He, Kaiming},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={7794--7803},
  year={2018}
}

Results and models

Cityscapes

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) config download
NonLocal R-50-D8 512x1024 40000 7.4 2.72 78.24 - config model | log
NonLocal R-101-D8 512x1024 40000 10.9 1.95 78.66 - config model | log
NonLocal R-50-D8 769x769 40000 8.9 1.52 78.33 79.92 config model | log
NonLocal R-101-D8 769x769 40000 12.8 1.05 78.57 80.29 config model | log
NonLocal R-50-D8 512x1024 80000 - - 78.01 - config model | log
NonLocal R-101-D8 512x1024 80000 - - 78.93 - config model | log
NonLocal R-50-D8 769x769 80000 - - 79.05 80.68 config model | log
NonLocal R-101-D8 769x769 80000 - - 79.40 80.85 config model | log

ADE20K

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) config download
NonLocal R-50-D8 512x512 80000 9.1 21.37 40.75 42.05 config model | log
NonLocal R-101-D8 512x512 80000 12.6 13.97 42.90 44.27 config model | log
NonLocal R-50-D8 512x512 160000 - - 42.03 43.04 config model | log
NonLocal R-101-D8 512x512 160000 - - 44.63 45.79 config model | log

Pascal VOC 2012 + Aug

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) config download
NonLocal R-50-D8 512x512 20000 6.4 21.21 76.20 77.12 config model | log
NonLocal R-101-D8 512x512 20000 9.8 14.01 78.15 78.86 config model | log
NonLocal R-50-D8 512x512 40000 - - 76.65 77.47 config model | log
NonLocal R-101-D8 512x512 40000 - - 78.27 79.12 config model | log