Skip to content

Commit

Permalink
update readme (#831)
Browse files Browse the repository at this point in the history
  • Loading branch information
@hellock
hellock authored Jun 19, 2019
1 parent 2d8fe05 commit 1b225a1
Show file tree
Hide file tree
Showing 2 changed files with 35 additions and 22 deletions.
2 changes: 1 addition & 1 deletion MODEL_ZOO.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
### Software environment

- Python 3.6 / 3.7
- PyTorch Nightly
- PyTorch 1.1
- CUDA 9.0.176
- CUDNN 7.0.4
- NCCL 2.1.15
Expand Down
55 changes: 34 additions & 21 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,7 @@

## Introduction

The master branch works with **PyTorch 1.1** or higher. If you would like to use PyTorch 0.4.1,
please checkout to the [pytorch-0.4.1](https://github.com/open-mmlab/mmdetection/tree/pytorch-0.4.1) branch.
The master branch works with **PyTorch 1.1** or higher.

mmdetection is an open source object detection toolbox based on PyTorch. It is
a part of the open-mmlab project developed by [Multimedia Laboratory, CUHK](http://mmlab.ie.cuhk.edu.hk/).
Expand All @@ -17,23 +16,21 @@ a part of the open-mmlab project developed by [Multimedia Laboratory, CUHK](http

- **Modular Design**

One can easily construct a customized object detection framework by combining different components.
We decompose the detection framework into different components and one can easily construct a customized object detection framework by combining different modules.

- **Support of multiple frameworks out of box**

The toolbox directly supports popular and contemporary detection frameworks, *e.g.* Faster RCNN, Mask RCNN, RetinaNet, etc.

- **High efficiency**

All basic bbox and mask operations run on GPUs now.
The training speed is nearly 2x faster than Detectron and comparable to maskrcnn-benchmark.
All basic bbox and mask operations run on GPUs now. The training speed is faster than or comparable to other codebases, including [Detectron](https://github.com/facebookresearch/Detectron), [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark) and [SimpleDet](https://github.com/TuSimple/simpledet).

- **State of the art**

This was the codebase of the *MMDet* team, who won the [COCO Detection 2018 challenge](http://cocodataset.org/#detection-leaderboard), and we keep pushing it forward.
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.

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.
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.

## License

Expand Down Expand Up @@ -83,26 +80,32 @@ v0.5.1 (20/10/2018)
Supported methods and backbones are shown in the below table.
Results and models are available in the [Model zoo](MODEL_ZOO.md).

| | ResNet | ResNeXt | SENet | VGG |
|--------------------|:--------:|:--------:|:--------:|:--------:|
| RPN | ✓ | ✓ | ☐ | ✗ |
| Fast R-CNN | ✓ | ✓ | ☐ | ✗ |
| Faster R-CNN | ✓ | ✓ | ☐ | ✗ |
| Mask R-CNN | ✓ | ✓ | ☐ | ✗ |
| Cascade R-CNN | ✓ | ✓ | ☐ | ✗ |
| Cascade Mask R-CNN | ✓ | ✓ | ☐ | ✗ |
| SSD | ✗ | ✗ | ✗ | ✓ |
| RetinaNet | ✓ | ✓ | ☐ | ✗ |
| Hybrid Task Cascade| ✓ | ✓ | ☐ | ✗ |
| FCOS | ✓ | ✓ | ☐ | ✗ |
| Libra R-CNN | ✓ | ✓ | ☐ | ✗ |
| | ResNet | ResNeXt | SENet | VGG | HRNet |
|--------------------|:--------:|:--------:|:--------:|:--------:|:-----:|
| RPN | ✓ | ✓ | ☐ | ✗ | ✓ |
| Fast R-CNN | ✓ | ✓ | ☐ | ✗ | ✓ |
| Faster R-CNN | ✓ | ✓ | ☐ | ✗ | ✓ |
| Mask R-CNN | ✓ | ✓ | ☐ | ✗ | ✓ |
| Cascade R-CNN | ✓ | ✓ | ☐ | ✗ | ✓ |
| Cascade Mask R-CNN | ✓ | ✓ | ☐ | ✗ | ✓ |
| SSD | ✗ | ✗ | ✗ | ✓ | ✗ |
| RetinaNet | ✓ | ✓ | ☐ | ✗ | ✓ |
| GHM | ✓ | ✓ | ☐ | ✗ | ✓ |
| Mask Scoring R-CNN | ✓ | ✓ | ☐ | ✗ | ✓ |
| FCOS | ✓ | ✓ | ☐ | ✗ | ✓ |
| Grid R-CNN | ✓ | ✓ | ☐ | ✗ | ✓ |
| Hybrid Task Cascade| ✓ | ✓ | ☐ | ✗ | ✓ |
| Libra R-CNN | ✓ | ✓ | ☐ | ✗ | ✓ |
| Guided Anchoring | ✓ | ✓ | ☐ | ✗ | ✓ |

Other features
- [x] DCNv2
- [x] Group Normalization
- [x] Weight Standardization
- [x] OHEM
- [x] Soft-NMS
- [x] Generalized Attention
- [x] GCNet
- [ ] Mixed Precision (FP16) Training (coming soon)


Expand All @@ -119,6 +122,11 @@ Please see [GETTING_STARTED.md](GETTING_STARTED.md) for the basic usage of MMDet

We appreciate all contributions to improve MMDetection. Please refer to [CONTRIBUTING.md](CONTRIBUTING.md) for the contributing guideline.

## Acknowledgement

MMDetection is an open source project that is contributed by researchers and engineers from various colledges 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.


## Citation

Expand All @@ -135,3 +143,8 @@ If you use this toolbox or benchmark in your research, please cite this project.
year = {2019}
}
```


## Contact

This repo is currently maintained by Kai Chen ([@hellock](http://github.com/hellock)), Jiangmiao Pang ([@OceanPang](https://github.com/OceanPang)), Jiaqi Wang ([@myownskyW7](https://github.com/myownskyW7)) and Yuhang Cao ([@yhcao6](https://github.com/yhcao6)).

0 comments on commit 1b225a1

Please sign in to comment.