Skip to content
Branch: master
Find file History
ppwwyyxx and facebook-github-bot put loss/inference to mask head
Summary: Prototype to make it easier to customize behavior of each head.

Reviewed By: rbgirshick

Differential Revision: D19743886

fbshipit-source-id: a7af7f50af97f6f6a6face29d3b5d5cfc12b68f5
Latest commit bbf3b16 Feb 14, 2020
Permalink
Type Name Latest commit message Commit time
..
Failed to load latest commit information.
configs/InstanceSegmentation Update docs Feb 6, 2020
point_rend put loss/inference to mask head Feb 14, 2020
README.md Add colab tutorial to the github README Feb 7, 2020
train_net.py PointRend instance segmentation Jan 30, 2020

README.md

PointRend: Image Segmentation as Rendering

Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick

[arXiv] [BibTeX]


In this repository, we release code for PointRend in Detectron2. PointRend can be flexibly applied to both instance and semantic (comming soon) segmentation tasks by building on top of existing state-of-the-art models.

Installation

Install Detectron 2 following INSTALL.md. You are ready to go!

Quick start and visualization

This Colab Notebook tutorial contains examples of PointRend usage and visualisations of its point sampling stages.

Training

To train a model with 8 GPUs run:

cd /path/to/detectron2/projects/PointRend
python train_net.py --config-file configs/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_coco.yaml --num-gpus 8

Evaluation

Model evaluation can be done similarly:

cd /path/to/detectron2/projects/PointRend
python train_net.py --config-file configs/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_coco.yaml --eval-only MODEL.WEIGHTS /path/to/model_checkpoint

Pretrained Models

Instance Segmentation

COCO

Mask
head
Backbone lr
sched
Output
resolution
mask
AP
mask
AP*
model id download
PointRend R50-FPN 224×224 36.2 38.3 164254221 model | metrics
PointRend R50-FPN 224×224 38.3 40.2 164955410 model | metrics

AP* is COCO mask AP evaluated against the higher-quality LVIS annotations; see the paper for details.

Cityscapes

Cityscapes model is trained with ImageNet pretraining.

Mask
head
Backbone lr
sched
Output
resolution
mask
AP
model id download
PointRend R50-FPN 224×224 35.9 164255101 model | metrics

Semantic Segmentation

[comming soon]

Citing PointRend

If you use PointRend, please use the following BibTeX entry.

@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}
}
You can’t perform that action at this time.