https://github.com/jianzhnie/retinanet_pytorch
RetinaNet in Pytorch
https://github.com/jianzhnie/retinanet_pytorch
Last synced: 6 months ago
JSON representation
RetinaNet in Pytorch
- Host: GitHub
- URL: https://github.com/jianzhnie/retinanet_pytorch
- Owner: jianzhnie
- Created: 2019-11-30T08:22:46.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2019-11-30T08:27:48.000Z (almost 6 years ago)
- Last Synced: 2025-02-14T11:53:05.620Z (8 months ago)
- Language: Python
- Size: 11.8 MB
- Stars: 1
- Watchers: 4
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# PyTorch-RetinaNet #
Pytorch implementation of RetinaNet object detection as described in [Focal Loss for Dense Object Detection](https://arxiv.org/abs/1708.02002) by Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He and Piotr Dollár.
This implementation is primarily designed to be easy to read and simple to modify.
## Training
The network can be trained using the `train.py` script.
```
python train.py
```
## Test
```
python test.py
```
## Pre-trained model
- Download the imagenet pretrain model resnet50 or resnet101 and put it in `weihts/resnet50.pth`
- Then run the script in `utils` folder, you will get an fpn pre-trained model
```
python utils/get_state_dict.py
```
### Reference:
- [Focal Loss for Dense Object Detection](https://arxiv.org/abs/1708.02002)
- Significant amounts of code are borrowed from the [keras retinanet implementation](https://github.com/fizyr/keras-retinanet)
- The NMS module used is from the [pytorch faster-rcnn implementation](https://github.com/ruotianluo/pytorch-faster-rcnn)