**News**: We released the technical report on [ArXiv](https://arxiv.org/abs/1906.07155).
This repo contains the supported code and configuration files to reproduce object detection results of [Swin Transformer](https://arxiv.org/pdf/2103.14030.pdf). It is based on [mmdetection](https://github.com/open-mmlab/mmdetection).
MMDetection is an open source object detection toolbox based on PyTorch. It is
a part of the [OpenMMLab](https://openmmlab.com/) project.
The master branch works with **PyTorch 1.3+**.
### Mask R-CNN
The old v1.x branch works with PyTorch 1.1 to 1.4, but v2.0 is strongly recommended for faster speed, higher performance, better design and more friendly usage.
We decompose the detection framework into different components and one can easily construct a customized object detection framework by combining different modules.
All basic bbox and mask operations run on GPUs. The training speed is faster than or comparable to other codebases, including [Detectron2](https://github.com/facebookresearch/detectron2), [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark) and [SimpleDet](https://github.com/TuSimple/simpledet).
**Notes**:
-**State of the art**
-**Pre-trained models can be downloaded from [Swin Transformer for ImageNet Classification](https://github.com/microsoft/Swin-Transformer)**.
- Access code for `baidu` is `swin`.
The toolbox stems from the codebase developed by the *MMDet* team, who won [COCO Detection Challenge](http://cocodataset.org/#detection-leaderboard) in 2018, and we keep pushing it forward.
## Usage
Apart from MMDetection, we also released a library [mmcv](https://github.com/open-mmlab/mmcv) for computer vision research, which is heavily depended on by this toolbox.
### Installation
## License
Please refer to [get_started.md](https://github.com/impiga/SwinTransformer-object-detection/blob/main/docs/get_started.md) for installation and dataset preparation.
This project is released under the [Apache 2.0 license](LICENSE).
Please see [get_started.md](docs/get_started.md) for the basic usage of MMDetection.
To train a detector with pre-trained models, run:
We provide [colab tutorial](demo/MMDet_Tutorial.ipynb), and full guidance for quick run [with existing dataset](docs/1_exist_data_model.md) and [with new dataset](docs/2_new_data_model.md) for beginners.
```
There are also tutorials for [finetuning models](docs/tutorials/finetune.md), [adding new dataset](docs/tutorials/new_dataset.md), [designing data pipeline](docs/tutorials/data_pipeline.md), [customizing models](docs/tutorials/customize_models.md), [customizing runtime settings](docs/tutorials/customize_runtime.md) and [useful tools](docs/useful_tools.md).
**Note:**`use_checkpoint` is used to save GPU memory. Please refer to [this page](https://pytorch.org/docs/stable/checkpoint.html) for more details.
We appreciate all contributions to improve MMDetection. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guideline.
## Acknowledgement
### Apex (optional):
We use apex for mixed precision training by default. To install apex, run:
MMDetection is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks.
```
We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new detectors.
If you use this toolbox or benchmark in your research, please cite this project.
If you would like to disable apex, modify the type of runner as `EpochBasedRunner` and comment out the following code block in the [configuration files](configs/swin):
```
# do not use mmdet version fp16
fp16 = None
optimizer_config = dict(
type="DistOptimizerHook",
update_interval=1,
grad_clip=None,
coalesce=True,
bucket_size_mb=-1,
use_fp16=True,
)
```
## Citing Swin Transformer
```
```
@article{mmdetection,
@article{liu2021Swin,
title = {{MMDetection}: Open MMLab Detection Toolbox and Benchmark},
title={Swin Transformer: Hierarchical Vision Transformer using Shifted Windows},
author = {Chen, Kai and Wang, Jiaqi and Pang, Jiangmiao and Cao, Yuhang and
author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
Xiong, Yu and Li, Xiaoxiao and Sun, Shuyang and Feng, Wansen and
journal={arXiv preprint arXiv:2103.14030},
Liu, Ziwei and Xu, Jiarui and Zhang, Zheng and Cheng, Dazhi and
year={2021}
Zhu, Chenchen and Cheng, Tianheng and Zhao, Qijie and Li, Buyu and
Lu, Xin and Zhu, Rui and Wu, Yue and Dai, Jifeng and Wang, Jingdong
and Shi, Jianping and Ouyang, Wanli and Loy, Chen Change and Lin, Dahua},
journal= {arXiv preprint arXiv:1906.07155},
year={2019}
}
}
```
```
## Projects in OpenMMLab
## Other Links
-[MMCV](https://github.com/open-mmlab/mmcv): OpenMMLab foundational library for computer vision.
> **Image Classification**: See [Swin Transformer for Image Classification](https://github.com/microsoft/Swin-Transformer).
-[MMClassification](https://github.com/open-mmlab/mmclassification): OpenMMLab image classification toolbox and benchmark.
-[MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab detection toolbox and benchmark.
> **Semantic Segmentation**: See [Swin Transformer for Semantic Segmentation](https://github.com/SwinTransformer/Swin-Transformer-Semantic-Segmentation).
-[MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab's next-generation platform for general 3D object detection.
-[MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab semantic segmentation toolbox and benchmark.
-[MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab's next-generation action understanding toolbox and benchmark.
-[MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab video perception toolbox and benchmark.
-[MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab pose estimation toolbox and benchmark.
-[MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab image and video editing toolbox.
