OpenMMLab Detection Toolbox and Benchmark https://mmdetection.readthedocs.io/
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
Guangchen Lin 9874180a01
[Enhance] Unify the interface of stuff head and panoptic head (#6308)
3 years ago
..
README.md
metafile.yml
panoptic_fpn_r50_fpn_1x_coco.py [Enhance] Unify the interface of stuff head and panoptic head (#6308) 3 years ago
panoptic_fpn_r50_fpn_mstrain_3x_coco.py
panoptic_fpn_r101_fpn_1x_coco.py
panoptic_fpn_r101_fpn_mstrain_3x_coco.py

README.md

Panoptic feature pyramid networks

Introduction

The base method for panoptic segmentation task.

@inproceedings{kirillov2018panopticfpn,
  author = {
    Alexander Kirillov,
    Ross Girshick,
    Kaiming He,
    Piotr Dollar,
  },
  title = {Panoptic Feature Pyramid Networks},
  booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019}
}

Dataset

PanopticFPN requires COCO and COCO-panoptic dataset for training and evaluation. You need to download and extract it in the COCO dataset path. The directory should be like this.

mmdetection
├── mmdet
├── tools
├── configs
├── data
│   ├── coco
│   │   ├── annotations
│   │   │   ├── panoptic_train2017.json
│   │   │   ├── panoptic_train2017
│   │   │   ├── panoptic_val2017.json
│   │   │   ├── panoptic_val2017
│   │   ├── train2017
│   │   ├── val2017
│   │   ├── test2017

Results and Models

Backbone style Lr schd Mem (GB) Inf time (fps) PQ SQ RQ PQ_th SQ_th RQ_th PQ_st SQ_st RQ_st Config Download
R-50-FPN pytorch 1x 4.7 40.2 77.8 49.3 47.8 80.9 57.5 28.9 73.1 37.0 config model | log
R-50-FPN pytorch 3x - - 42.5 78.1 51.7 50.3 81.5 60.3 30.7 73.0 38.8 config model | log
R-101-FPN pytorch 1x 6.7 42.2 78.3 51.4 50.1 81.4 59.9 30.3 73.6 38.5 config model | log
R-101-FPN pytorch 3x - - 44.1 78.9 53.6 52.1 81.7 62.3 32.0 74.6 40.3 config model | log