kadirnar commited on
Commit
0a7b212
1 Parent(s): 1bde08f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -0
README.md CHANGED
@@ -1,3 +1,55 @@
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/yolov6-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
+ ### Yolov6 Inference
26
+ ```python
27
+ from yoloxdetect import YoloxDetect
28
+ from yolox.data.datasets import COCO_CLASSES
29
+
30
+ model = YoloxDetect(
31
+ model_path = "data/weights/yolox_s.pth",
32
+ config_path = "configs.yolox_s",
33
+ device = "cuda:0",
34
+ classes = COCO_CLASSES,
35
+ confidence_threshold = 0.25,
36
+ nms_threshold = 0.45,
37
+ )
38
+ model.classes = COCO_CLASSES
39
+ model.conf = 0.25
40
+ model.iou = 0.45
41
+ model.show = False
42
+ model.save = True
43
+
44
+ pred = model.predict(image='data/images', img_size=640)
45
+ ```
46
+
47
+ ### BibTeX Entry and Citation Info
48
+ ```
49
+ @article{yolox2021,
50
+ title={YOLOX: Exceeding YOLO Series in 2021},
51
+ author={Ge, Zheng and Liu, Songtao and Wang, Feng and Li, Zeming and Sun, Jian},
52
+ journal={arXiv preprint arXiv:2107.08430},
53
+ year={2021}
54
+ }
55
+ ```