MaochengHu 576cda45b8 first commit | 2 years ago | |
---|---|---|
.. | ||
_base_ | 2 years ago | |
README.md | 2 years ago | |
detr_r50_1x_coco.yml | 2 years ago |
DETR is an object detection model based on transformer. We reproduced the model of the paper.
Backbone | Model | Images/GPU | Inf time (fps) | Box AP | Config | Download |
---|---|---|---|---|---|---|
R-50 | DETR | 4 | --- | 42.3 | 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/detr/detr_r50_1x_coco.yml --fleet
@inproceedings{detr,
author = {Nicolas Carion and
Francisco Massa and
Gabriel Synnaeve and
Nicolas Usunier and
Alexander Kirillov and
Sergey Zagoruyko},
title = {End-to-End Object Detection with Transformers},
booktitle = {ECCV},
year = {2020}
}