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 321eb30034
[Enhancement] Modify metafiles (#5496)
3 years ago
..
README.md change to https (#5328) 3 years ago
metafile.yml [Enhancement] Modify metafiles (#5496) 3 years ago
point_rend_r50_caffe_fpn_mstrain_1x_coco.py Move train_cfg/test_cfg into model (#4347) 4 years ago
point_rend_r50_caffe_fpn_mstrain_3x_coco.py [Fix]: Add types of runner in configs (#4669) 4 years ago

README.md

PointRend

Introduction

@InProceedings{kirillov2019pointrend,
  title={{PointRend}: Image Segmentation as Rendering},
  author={Alexander Kirillov and Yuxin Wu and Kaiming He and Ross Girshick},
  journal={ArXiv:1912.08193},
  year={2019}
}

Results and models

Backbone Style Lr schd Mem (GB) Inf time (fps) box AP mask AP Config Download
R-50-FPN caffe 1x 4.6 38.4 36.3 config model | log
R-50-FPN caffe 3x 4.6 41.0 38.0 config model | log

Note: All models are trained with multi-scale, the input image shorter side is randomly scaled to one of (640, 672, 704, 736, 768, 800).