CenterNet: Objects as Points + CondInst: Conditional Convolutions for Instance Segmentation
Please refer to CnterNet INSTALL.md for installation instructions.
## 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 20 --master_batch 9 --lr 1.25e-4 --gpus 0,1 --num_workers 4
## not support flip test and multi scale test
cd src
python test.py ctseg --exp_id coco_dla_1x --keep_res --resume
cd src
python demo.py ctseg --exp_id coco_dla_1x --keep_res --resume --demo ../data/coco/val2017
type | AP | AP50 | AP75 | APs | APm | APl |
---|---|---|---|---|---|---|
box | 0.358 | 0.540 | 0.384 | 0.154 | 0.391 | 0.535 |
mask | 0.306 | 0.493 | 0.317 | 0.100 | 0.341 | 0.490 |
backbone=dla_34, batch=32