https://github.com/res2net/res2net-detectron2
Res2Net for Panoptic Segmentation based on detectron2 (SOTA results).
https://github.com/res2net/res2net-detectron2
detectron2 multi-scale panoptic res2net segmentation sota
Last synced: 4 days ago
JSON representation
Res2Net for Panoptic Segmentation based on detectron2 (SOTA results).
- Host: GitHub
- URL: https://github.com/res2net/res2net-detectron2
- Owner: Res2Net
- License: apache-2.0
- Created: 2020-05-11T07:03:23.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2020-06-08T02:13:16.000Z (almost 5 years ago)
- Last Synced: 2024-04-23T00:23:22.815Z (about 1 year ago)
- Topics: detectron2, multi-scale, panoptic, res2net, segmentation, sota
- Language: Python
- Homepage: https://mmcheng.net/res2net/
- Size: 630 KB
- Stars: 30
- Watchers: 3
- Forks: 11
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- Contributing: .github/CONTRIBUTING.md
- License: LICENSE
- Code of conduct: .github/CODE_OF_CONDUCT.md
Awesome Lists containing this project
README
# Res2Net for Panoptic Segmentation based on detectron2.
## Introduction
We propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer.
## Performance on COCO dataset
Name
lr
sched
train
mem
(GB)
box
AP
mask
AP
PQ
download
R50-FPN
1x
4.8
37.6
34.7
39.4
model | metrics
R50-FPN
3x
4.8
40.0
36.5
41.5
model | metrics
R101-FPN
3x
6.0
42.4
38.5
43.0
model | metrics
Res2Net101-FPN
3x
6.0
44.0
39.6
44.5
model | metrics
- Res2Net101 has the similar parameters and FLOPs compared with ResNet101.
- We only test and show results of Panoptic Segmentation on detectron2, the detection and instance segmentation on detectron2 is also supported in this repo.
- Res2Net ImageNet pretrained models are in [Res2Net-PretrainedModels](https://github.com/Res2Net/Res2Net-PretrainedModels).
- More applications of Res2Net are in [Res2Net-Github](https://github.com/Res2Net/).
## Usage
- Use the tools/convert-torchvision-to-d2.py to transfer the ImageNet pretrained model of Res2Net101 to detectron2 supported format. Or just download the converted model from
this [link](https://mailnankaieducn-my.sharepoint.com/:u:/g/personal/shgao_mail_nankai_edu_cn/EZhtWgMRlxpGtJmtJ2zP1_QBqvmu_FJ05vUgOq30ElT9yg?e=e5FRD8).
- Use the command to train:
```
./tools/train_net.py --num-gpus 8 --config-file configs/COCO-PanopticSegmentation/panoptic_fpn_R2_101_3x.yaml
```
## Citation
If you find this work or code is helpful in your research, please cite:
```
@article{gao2019res2net,
title={Res2Net: A New Multi-scale Backbone Architecture},
author={Gao, Shang-Hua and Cheng, Ming-Ming and Zhao, Kai and Zhang, Xin-Yu and Yang, Ming-Hsuan and Torr, Philip},
journal={IEEE TPAMI},
year={2020},
doi={10.1109/TPAMI.2019.2938758},
}
```
For more details of detectron2, please refer to
the detectron2 repo.
Detectron2 is Facebook AI Research's next generation software system
that implements state-of-the-art object detection algorithms.
It is a ground-up rewrite of the previous version,
[Detectron](https://github.com/facebookresearch/Detectron/),
and it originates from [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark/).
### What's New
* It is powered by the [PyTorch](https://pytorch.org) deep learning framework.
* Includes more features such as panoptic segmentation, densepose, Cascade R-CNN, rotated bounding boxes, etc.
* Can be used as a library to support [different projects](projects/) on top of it.
We'll open source more research projects in this way.
* It [trains much faster](https://detectron2.readthedocs.io/notes/benchmarks.html).
See our [blog post](https://ai.facebook.com/blog/-detectron2-a-pytorch-based-modular-object-detection-library-/)
to see more demos and learn about detectron2.
## Installation
See [INSTALL.md](INSTALL.md).
## Quick Start
See [GETTING_STARTED.md](GETTING_STARTED.md),
or the [Colab Notebook](https://colab.research.google.com/drive/16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5).
Learn more at our [documentation](https://detectron2.readthedocs.org).
And see [projects/](projects/) for some projects that are built on top of detectron2.
## Model Zoo and Baselines
We provide a large set of baseline results and trained models available for download in the [Detectron2 Model Zoo](MODEL_ZOO.md).
## License
Detectron2 is released under the [Apache 2.0 license](LICENSE).
## Citing Detectron2
If you use Detectron2 in your research or wish to refer to the baseline results published in the [Model Zoo](MODEL_ZOO.md), please use the following BibTeX entry.
```BibTeX
@misc{wu2019detectron2,
author = {Yuxin Wu and Alexander Kirillov and Francisco Massa and
Wan-Yen Lo and Ross Girshick},
title = {Detectron2},
howpublished = {\url{https://github.com/facebookresearch/detectron2}},
year = {2019}
}
```