https://github.com/Megvii-BaseDetection/AutoAssign
Pytorch implementation of "AutoAssign: Differentiable Label Assignment for Dense Object Detection"
https://github.com/Megvii-BaseDetection/AutoAssign
coco-dataset computer-vision object-detection
Last synced: about 1 month ago
JSON representation
Pytorch implementation of "AutoAssign: Differentiable Label Assignment for Dense Object Detection"
- Host: GitHub
- URL: https://github.com/Megvii-BaseDetection/AutoAssign
- Owner: Megvii-BaseDetection
- License: apache-2.0
- Created: 2020-12-02T08:08:03.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2020-12-07T12:15:00.000Z (over 4 years ago)
- Last Synced: 2024-07-31T21:53:43.062Z (9 months ago)
- Topics: coco-dataset, computer-vision, object-detection
- Language: Python
- Homepage:
- Size: 342 KB
- Stars: 140
- Watchers: 8
- Forks: 18
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-anchor-free-object-detection - AutoAssign - BaseDetection/AutoAssign?style=social"/> : "AutoAssign: Differentiable Label Assignment for Dense Object Detection". (**[arXiv 2020](https://arxiv.org/abs/2007.03496)**) (Frameworks)
README
# AutoAssign: Differentiable Label Assignment for Dense Object Detection
# 
This is a PyTorch implementation of the [AutoAssign paper](https://arxiv.org/abs/2007.03496):
```
@article{zhu2020autoassign,
title={AutoAssign: Differentiable Label Assignment for Dense Object Detection},
author={Zhu, Benjin and Wang, Jianfeng and Jiang, Zhengkai and Zong, Fuhang and Liu, Songtao and Li, Zeming and Sun, Jian},
journal={arXiv preprint arXiv:2007.03496},
year={2020}
}
```
## Get Started
1. install [cvpods](https://github.com/Megvii-BaseDetection/cvpods) following the instructions
```shell
# Install cvpods
git clone https://github.com/Megvii-BaseDetection/cvpods
cd cvpods
## build cvpods (requires GPU)
pip install -r requirements.txt
python setup.py build develop
## preprare data path
mkdir datasets
ln -s /path/to/your/coco/dataset datasets/coco
```
2. run the project
```shell
cd auto_assign.res50.fpn.coco.800size.1x
# train
pods_train --num-gpus 8
# test
pods_test --num-gpus 8
# test with provided weights
pods_test --num-gpus 8 MODEL.WEIGHTS /path/to/your/model.pth
```
## Results
| Model | Multi-scale training | Multi-scale testing | Testing time / im | AP (minival) | Link |
|:--- |:--------------------:|:--------------------:|:-----------------:|:-------:|:---:|
| [AutoAssign_Res50_FPN_1x](https://github.com/poodarchu/AutoAssign/blob/master/auto_assign.res50.fpn.coco.800size.1x/config.py) | No | No | 53ms | 40.5 | [download](https://drive.google.com/file/d/11mV53SJUIpCdWj-Wbfi_fdmDz96ekb-Z/view?usp=sharing)