https://github.com/vietanhdev/centernet-bdd-data-onnx-conversion

centernet-to-onnx-conversion
https://github.com/vietanhdev/centernet-bdd-data-onnx-conversion

Last synced: 10 months ago
JSON representation

centernet-to-onnx-conversion

• Host: GitHub
• URL: https://github.com/vietanhdev/centernet-bdd-data-onnx-conversion
• Owner: vietanhdev
• License: mit
• Created: 2020-11-15T12:35:58.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2020-11-15T12:38:57.000Z (over 5 years ago)
• Last Synced: 2025-04-03T19:11:08.387Z (about 1 year ago)
• Language: Python
• Homepage:
• Size: 6.14 MB
• Stars: 1
• Watchers: 2
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Objects as Points - For BDD dataset - ONNX Conversion

Object detection, 3D detection, and pose estimation using center point detection:

![](readme/fig2.png)

> [**Objects as Points**](http://arxiv.org/abs/1904.07850),            

> Xingyi Zhou, Dequan Wang, Philipp Krähenbühl,        

> *arXiv technical report ([arXiv 1904.07850](http://arxiv.org/abs/1904.07850))*         

This project is based on original CenterNet - Objects as Points from [https://github.com/xingyizhou/CenterNet](https://github.com/xingyizhou/CenterNet). I added some customizations to train CenterNet on [BDD100k dataset](https://bdd-data.berkeley.edu/) for my advanced driver-assistance system project. The detailed training result can be found at [this blog post](https://aicurious.io/posts/adas-jetson-nano-intro-and-hardware/).

Notice that this repository was modified using [this instruction](https://github.com/CaoWGG/TensorRT-CenterNet/blob/master/readme/ctdet2onnx.md) and should only be used for converting models to ONNX format. Pay attention to use right version of PyTorch for this repository (v1.0 or v1.1 instead of v0.4.1 like in training environment).

Please use [original repository](https://github.com/xingyizhou/CenterNet) or [this repository](https://github.com/vietanhdev/centernet-bdd-data) to train models.

## License

CenterNet itself is released under the MIT License (refer to the LICENSE file for details).

Portions of the code are borrowed from [human-pose-estimation.pytorch](https://github.com/Microsoft/human-pose-estimation.pytorch) (image transform, resnet), [CornerNet](https://github.com/princeton-vl/CornerNet) (hourglassnet, loss functions), [dla](https://github.com/ucbdrive/dla) (DLA network), [DCNv2](https://github.com/CharlesShang/DCNv2)(deformable convolutions), [tf-faster-rcnn](https://github.com/endernewton/tf-faster-rcnn)(Pascal VOC evaluation) and [kitti_eval](https://github.com/prclibo/kitti_eval) (KITTI dataset evaluation). Please refer to the original License of these projects (See [NOTICE](NOTICE)).

## Citation

If you find this project useful for your research, please use the following BibTeX entry.

    @inproceedings{zhou2019objects,

      title={Objects as Points},

      author={Zhou, Xingyi and Wang, Dequan and Kr{\"a}henb{\"u}hl, Philipp},

      booktitle={arXiv preprint arXiv:1904.07850},

      year={2019}

    }