https://github.com/jahongir7174/sparsercnn
Sparse Mask R-CNN implementation using PyTorch
https://github.com/jahongir7174/sparsercnn
instance-segmentation mixup mosaic object-detection pytorch swin-transformer
Last synced: 6 months ago
JSON representation
Sparse Mask R-CNN implementation using PyTorch
- Host: GitHub
- URL: https://github.com/jahongir7174/sparsercnn
- Owner: jahongir7174
- License: mit
- Created: 2022-05-30T05:54:03.000Z (over 3 years ago)
- Default Branch: master
- Last Pushed: 2022-06-08T05:31:06.000Z (over 3 years ago)
- Last Synced: 2025-03-24T12:46:59.633Z (7 months ago)
- Topics: instance-segmentation, mixup, mosaic, object-detection, pytorch, swin-transformer
- Language: Python
- Homepage:
- Size: 31.3 KB
- Stars: 3
- Watchers: 0
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
[Sparse Mask R-CNN](https://arxiv.org/abs/2105.01928) implementation using PyTorch
### Install
* `pip install mmcv-full==1.5.2`
* `pip install mmdet==2.25.0`
### Train
* `bash ./main.sh ./nets/exp01.py $ --train` for training, `$` is number of GPUs
### Results
| Detector | Backbone | Neck | LR Schedule | Box mAP | Mask mAP | Config |
|:------------:|:---------:|:-----:|:-----------:|--------:|---------:|-------:|
| Sparse R-CNN | ResNet-50 | FPN | 1x | - | - | exp01 |
| Sparse R-CNN | ResNet-50 | FPN | 1x | - | - | exp02 |
| Sparse R-CNN | ResNet-50 | PAFPN | 1x | - | - | exp03 |
| Sparse R-CNN | ResNet-50 | PAFPN | 3x | - | - | exp04 |
### TODO
* [x] [exp01](./nets/exp01.py), default [Sparse R-CNN](https://arxiv.org/abs/2105.01928)
* [x] [exp02](./nets/exp02.py), added [GN](https://arxiv.org/abs/1803.08494) and [WS](https://arxiv.org/abs/1903.10520)
* [x] [exp03](./nets/exp04.py), added [PAFPN](https://arxiv.org/abs/1803.01534)
* [x] [exp04](./nets/exp04.py), added [MOSAIC](https://arxiv.org/abs/2004.10934),
[MixUp](https://arxiv.org/abs/1710.09412) and [CopyPaste](https://arxiv.org/abs/2012.07177)
### Reference
* https://github.com/ultralytics/yolov5
* https://github.com/open-mmlab/mmdetection