MaochengHu 576cda45b8 first commit | před 2 roky | |
---|---|---|
.. | ||
_base_ | před 2 roky | |
README.md | před 2 roky | |
tood_r50_fpn_1x_coco.yml | před 2 roky |
TOOD: Task-aligned One-stage Object Detection
TOOD is an object detection model. We reproduced the model of the paper.
Backbone | Model | Images/GPU | Inf time (fps) | Box AP | Config | Download |
---|---|---|---|---|---|---|
R-50 | TOOD | 4 | --- | 42.5 | config | model |
Notes:
mAP(IoU=0.5:0.95)
.GPU multi-card training
export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/tood/tood_r50_fpn_1x_coco.yml --fleet
@inproceedings{feng2021tood,
title={TOOD: Task-aligned One-stage Object Detection},
author={Feng, Chengjian and Zhong, Yujie and Gao, Yu and Scott, Matthew R and Huang, Weilin},
booktitle={ICCV},
year={2021}
}