https://github.com/losttech/yolov4
Port of YOLOv4 to C# + TensorFlow
https://github.com/losttech/yolov4
Last synced: 9 months ago
JSON representation
Port of YOLOv4 to C# + TensorFlow
- Host: GitHub
- URL: https://github.com/losttech/yolov4
- Owner: losttech
- License: mit
- Created: 2020-10-14T06:00:43.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2020-12-29T02:58:50.000Z (about 5 years ago)
- Last Synced: 2025-04-20T01:33:02.321Z (10 months ago)
- Language: C#
- Size: 3.78 MB
- Stars: 12
- Watchers: 2
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# YOLOv4
[](LICENSE)
*NOTICE: This is a port of https://github.com/hunglc007/tensorflow-yolov4-tflite
YOLOv4 Implemented in Tensorflow 1.15
### Prerequisites
[](https://www.nuget.org/packages/LostTech.TensorFlow)
### Performance
### Demo
TBD
#### Output
##### Yolov4 original weight
##### Yolov4 tflite int8
### Convert to ONNX
TBD
### Evaluate on COCO 2017 Dataset
TBD
# evaluate yolov4 model
TBD
#### mAP50 on COCO 2017 Dataset
| Detection | 512x512 | 416x416 | 320x320 |
|-------------|---------|---------|---------|
| YoloV3 | 55.43 | | |
| YoloV4 | 61.96 | 57.33 | |
### Benchmark
TBD
#### Tesla P100
| Detection | 512x512 | 416x416 | 320x320 |
|-------------|---------|---------|---------|
| YoloV3 FPS | 40.6 | 49.4 | 61.3 |
| YoloV4 FPS | 33.4 | 41.7 | 50.0 |
#### Tesla K80
| Detection | 512x512 | 416x416 | 320x320 |
|-------------|---------|---------|---------|
| YoloV3 FPS | 10.8 | 12.9 | 17.6 |
| YoloV4 FPS | 9.6 | 11.7 | 16.0 |
#### Tesla T4
| Detection | 512x512 | 416x416 | 320x320 |
|-------------|---------|---------|---------|
| YoloV3 FPS | 27.6 | 32.3 | 45.1 |
| YoloV4 FPS | 24.0 | 30.3 | 40.1 |
#### Tesla P4
| Detection | 512x512 | 416x416 | 320x320 |
|-------------|---------|---------|---------|
| YoloV3 FPS | 20.2 | 24.2 | 31.2 |
| YoloV4 FPS | 16.2 | 20.2 | 26.5 |
#### Macbook Pro 15 (2.3GHz i7)
| Detection | 512x512 | 416x416 | 320x320 |
|-------------|---------|---------|---------|
| YoloV3 FPS | | | |
| YoloV4 FPS | | | |
### Traning your own model
Sample training code available at [samples/TrainV4](samples/TrainV4)
### References
* YOLOv4: Optimal Speed and Accuracy of Object Detection [YOLOv4](https://arxiv.org/abs/2004.10934).
* [darknet](https://github.com/AlexeyAB/darknet)
My project is inspired by these previous fantastic YOLOv3 implementations:
* [Yolov3 tensorflow](https://github.com/YunYang1994/tensorflow-yolov3)
* [Yolov3 tf2](https://github.com/zzh8829/yolov3-tf2)