https://github.com/xiaochus/YOLOv3
Keras implementation of yolo v3 object detection.
https://github.com/xiaochus/YOLOv3
cnn keras object-detection yolov3
Last synced: about 2 months ago
JSON representation
Keras implementation of yolo v3 object detection.
- Host: GitHub
- URL: https://github.com/xiaochus/YOLOv3
- Owner: xiaochus
- License: mit
- Created: 2018-04-09T13:28:13.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2022-09-26T19:22:28.000Z (over 2 years ago)
- Last Synced: 2024-11-09T13:39:04.495Z (7 months ago)
- Topics: cnn, keras, object-detection, yolov3
- Language: Python
- Homepage:
- Size: 13.6 MB
- Stars: 607
- Watchers: 23
- Forks: 267
- Open Issues: 17
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-yolo-object-detection - xiaochus/YOLOv3
- awesome-yolo-object-detection - xiaochus/YOLOv3
README
# YOLOv3
Keras(TF backend) implementation of yolo v3 objects detection.
According to the paper [YOLOv3: An Incremental Improvement](https://pjreddie.com/media/files/papers/YOLOv3.pdf).
## Requirement
- OpenCV 3.4
- Python 3.6
- Tensorflow-gpu 1.5.0
- Keras 2.1.3
## Quick start
- Download official [yolov3.weights](https://pjreddie.com/media/files/yolov3.weights) and put it on top floder of project.
- Run the follow command to convert darknet weight file to keras h5 file. The `yad2k.py` was modified from [allanzelener/YAD2K](https://github.com/allanzelener/YAD2K).
```
python yad2k.py cfg\yolo.cfg yolov3.weights data\yolo.h5
```
- run follow command to show the demo. The result can be found in `images\res\` floder.
```
python demo.py
```
## Demo result
It can be seen that yolo v3 has a better classification ability than yolo v2.
## TODO
- Train the model.
## Reference
@article{YOLOv3,
title={YOLOv3: An Incremental Improvement},
author={J Redmon, A Farhadi },
year={2018}
## Copyright
See [LICENSE](LICENSE) for details.