OneNet: Towards End-to-End One-Stage Object Detection
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.
Introduction
OneNet: Towards End-to-End One-Stage Object Detection
Updates
- (11/12/2020) Higher Performance for OneNet is reported by disable gradient clip.
Comming
- Provide models and logs
- Support to caffe, onnx, tensorRT
- Support to Res18, MobileNet
Models
We provide two models
- R50_dcn is for high accuracy
- R50_nodcn is for easy deployment.
Method | inf_time | train_time | box AP | download |
---|---|---|---|---|
R50_dcn | 67 FPS | 36h | 35.7 | |
R50_nodcn | 73 FPS | 29h | 32.7 |
Notes
- We observe about 0.3 AP noise.
- The training time and inference time are on 8 NVIDIA V100 GPUs.
Installation
The codebases are built on top of Detectron2 and DETR.
Requirements
- Linux or macOS with Python ≥ 3.6
- PyTorch ≥ 1.5 and torchvision that matches the PyTorch installation. You can install them together at pytorch.org to make sure of this
- OpenCV is optional and needed by demo and visualization
Steps
- Install and build libs
git clone https://github.com/PeizeSun/OneNet.git
cd OneNet
python setup.py build develop
- Link coco dataset path to OneNet/datasets/coco
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
- Train OneNet
python projects/OneNet/train_net.py --num-gpus 8 \
--config-file projects/OneNet/configs/onenet.res50.dcn.yaml
- Evaluate OneNet
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
- Visualize OneNet
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
License
OneNet is released under MIT License.
Citing
If you use OneNet in your research or wish to refer to the baseline results published here, please use the following BibTeX entries:
@article{peize2020onenet,
title = {{OneNet}: Towards End-to-End One-Stage Object Detection},
author = {Peize Sun and Yi Jiang and Enze Xie and Zehuan Yuan and Changhu Wang and Ping Luo},
journal = {arXiv preprint arXiv: },
year = {2020}
}