Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
root 9a4a4147df | 1 year ago | |
---|---|---|
.circleci | 1 year ago | |
.github | 1 year ago | |
configs | 1 year ago | |
datasets | 1 year ago | |
demo | 1 year ago | |
demo_d2 | 1 year ago | |
detectron2 | 1 year ago | |
dev | 1 year ago | |
docker | 1 year ago | |
docs | 1 year ago | |
projects | 1 year ago | |
tests | 1 year ago | |
tools | 1 year ago | |
.clang-format | 1 year ago | |
.flake8 | 1 year ago | |
.gitignore | 1 year ago | |
GETTING_STARTED.md | 1 year ago | |
INSTALL.md | 1 year ago | |
LICENSE | 1 year ago | |
MODEL_ZOO.md | 1 year ago | |
R-50.zip | 1 year ago | |
README.md | 1 year ago | |
README_d2.md | 1 year ago | |
colormap.py | 1 year ago | |
onenet.jpeg | 1 year ago | |
run.py | 1 year ago | |
run1.py | 1 year ago | |
se_resnet50.zip | 1 year ago | |
setup.cfg | 1 year ago | |
setup.py | 1 year ago |
Comparisons of different label assignment methods. H and W are height and width of feature map, respectively,
K is number of object categories. Previous works on one-stage object detection assign labels by only position cost, such
as (a) box IoU or (b) point distance between sample and ground-truth. In our method, however, (c) classification cost is
additionally introduced. We discover that classification cost is the key to the success of end-to-end. Without classification
cost, only location cost leads to redundant boxes of high confidence scores in inference, making NMS post-processing a
necessary component.
arxiv: OneNet: Towards End-to-End One-Stage Object Detection
paper: What Makes for End-to-End Object Detection?
We provide two models
Method | inf_time | train_time | box AP | download |
---|---|---|---|---|
R18_dcn | 109 FPS | 20h | 29.9 | model | log |
R18_nodcn | 138 FPS | 13h | 27.7 | model | log |
R50_dcn | 67 FPS | 36h | 35.7 | model | log |
R50_nodcn | 73 FPS | 29h | 32.7 | model | log |
R50_RetinaNet | 26 FPS | 31h | 37.5 | model | log |
R50_FCOS | 27 FPS | 21h | 38.9 | model | log |
Models are available in Baidu Drive by code nhr8.
Method | inf_time | train_time | AP50 | mMR | recall | download |
---|---|---|---|---|---|---|
R50_RetinaNet | 26 FPS | 11.5h | 90.9 | 48.8 | 98.0 | model | log |
R50_FCOS | 27 FPS | 4.5h | 90.6 | 48.6 | 97.7 | model | log |
Models are available in Baidu Drive by code nhr8.
The codebases are built on top of Detectron2 and DETR.
git clone https://github.com/PeizeSun/OneNet.git
cd OneNet
python setup.py build develop
mkdir -p datasets/coco
ln -s /path_to_coco_dataset/annotations datasets/coco/annotations
ln -s /path_to_coco_dataset/train2017 datasets/coco/train2017
ln -s /path_to_coco_dataset/val2017 datasets/coco/val2017
python projects/OneNet/train_net.py --num-gpus 8 \
--config-file projects/OneNet/configs/onenet.res50.dcn.yaml
python projects/OneNet/train_net.py --num-gpus 8 \
--config-file projects/OneNet/configs/onenet.res50.dcn.yaml \
--eval-only MODEL.WEIGHTS path/to/model.pth
python demo/demo.py\
--config-file projects/OneNet/configs/onenet.res50.dcn.yaml \
--input path/to/images --output path/to/save_images --confidence-threshold 0.4 \
--opts MODEL.WEIGHTS path/to/model.pth
OneNet is released under MIT License.
If you use OneNet in your research or wish to refer to the baseline results published here, please use the following BibTeX entries:
@InProceedings{peize2020onenet,
title = {What Makes for End-to-End Object Detection?},
author = {Sun, Peize and Jiang, Yi and Xie, Enze and Shao, Wenqi and Yuan, Zehuan and Wang, Changhu and Luo, Ping},
booktitle = {Proceedings of the 38th International Conference on Machine Learning},
pages = {9934--9944},
year = {2021},
volume = {139},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
}
No Description
Python Cuda C++ Markdown Shell other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》