flyingshan/centercondinst

Instance Segmentation based on CenterNet and CondInst.

CenterNet-CondInst

CenterNet: Objects as Points + CondInst: Conditional Convolutions for Instance Segmentation

Installation

Please refer to CnterNet INSTALL.md for installation instructions.

Training

## note : seg_weight default setting is 1. You can set it to other value to get better performance.
cd src
python main.py ctseg --exp_id coco_dla_1x --batch_size 4 --lr 1.25e-4 --gpus 0 --num_workers 4 --num_epochs 70

Eval

## not support flip test and multi scale test
cd src
python test.py ctseg --exp_id coco_dla_1x --resume

Visualization

cd src
python demo.py ctseg --exp_id coco_dla_1x --load_model ../exp/ctseg/coco_dla_1x/epoch_75.pth --demo ../images/

Result

(TODO)

Reference

1. CenterNet
2. CondInst
3. CondInst-AdelaiDet
4. CenterNet-CondInst