Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,50 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- object-detection
|
5 |
+
- computer-vision
|
6 |
+
- yolox
|
7 |
+
- yolov3
|
8 |
+
- yolov5
|
9 |
+
datasets:
|
10 |
+
- detection-datasets/coco
|
11 |
---
|
12 |
+
|
13 |
+
### Model Description
|
14 |
+
[YOLOX](https://arxiv.org/abs/2107.08430) is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported.
|
15 |
+
|
16 |
+
[YOLOXDetect-Pip](https://github.com/kadirnar/yolox-pip/): This repo is a packaged version of the [YOLOX](https://github.com/Megvii-BaseDetection/YOLOX) for easy installation and use.
|
17 |
+
|
18 |
+
[Paper Repo]: Implementation of paper - [YOLOX](https://github.com/Megvii-BaseDetection/YOLOX)
|
19 |
+
|
20 |
+
### Installation
|
21 |
+
```
|
22 |
+
pip install yoloxdetect
|
23 |
+
```
|
24 |
+
|
25 |
+
### Yolox Inference
|
26 |
+
```python
|
27 |
+
from yoloxdetect import YoloxDetector
|
28 |
+
from yolox.data.datasets import COCO_CLASSES
|
29 |
+
model = YoloxDetector(
|
30 |
+
model_path = "kadirnar/yolox_nano-v0.1.1",
|
31 |
+
config_path = "configs.yolox_s",
|
32 |
+
device = "cuda:0",
|
33 |
+
)
|
34 |
+
model.classes = COCO_CLASSES
|
35 |
+
model.conf = 0.25
|
36 |
+
model.iou = 0.45
|
37 |
+
model.show = False
|
38 |
+
model.save = True
|
39 |
+
pred = model.predict(image='data/images', img_size=640)
|
40 |
+
```
|
41 |
+
|
42 |
+
### BibTeX Entry and Citation Info
|
43 |
+
```
|
44 |
+
@article{yolox2021,
|
45 |
+
title={YOLOX: Exceeding YOLO Series in 2021},
|
46 |
+
author={Ge, Zheng and Liu, Songtao and Wang, Feng and Li, Zeming and Sun, Jian},
|
47 |
+
journal={arXiv preprint arXiv:2107.08430},
|
48 |
+
year={2021}
|
49 |
+
}
|
50 |
+
```
|