HugoHE commited on
Commit
4939689
·
verified ·
1 Parent(s): fab8fc5

Add comprehensive model card for yolov10-bdd-vanilla

Browse files
Files changed (1) hide show
  1. README.md +108 -0
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: ultralytics
4
+ tags:
5
+ - yolov10
6
+ - object-detection
7
+ - computer-vision
8
+ - pytorch
9
+ - bdd100k
10
+ - autonomous-driving
11
+ - BDD 100K
12
+ - from-scratch
13
+ pipeline_tag: object-detection
14
+ datasets:
15
+ - bdd100k
16
+ widget:
17
+ - src: https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bounding-boxes-sample.png
18
+ example_title: "Sample Image"
19
+ model-index:
20
+ - name: yolov10-bdd-vanilla
21
+ results:
22
+ - task:
23
+ type: object-detection
24
+ dataset:
25
+ type: bdd100k
26
+ name: Berkeley DeepDrive (BDD) 100K
27
+ metrics:
28
+ - type: mean_average_precision
29
+ name: mAP
30
+ value: "TBD"
31
+ ---
32
+
33
+ # YOLOv10 - Berkeley DeepDrive (BDD) 100K Vanilla
34
+
35
+ YOLOv10 model trained from scratch on Berkeley DeepDrive (BDD) 100K dataset for object detection in autonomous driving scenarios.
36
+
37
+ ## Model Details
38
+
39
+ - **Model Type**: YOLOv10 Object Detection
40
+ - **Dataset**: Berkeley DeepDrive (BDD) 100K
41
+ - **Training Method**: trained from scratch
42
+ - **Framework**: PyTorch/Ultralytics
43
+ - **Task**: Object Detection
44
+
45
+ ## Dataset Information
46
+
47
+ This model was trained on the **Berkeley DeepDrive (BDD) 100K** dataset, which contains the following object classes:
48
+
49
+ car, truck, bus, motorcycle, bicycle, person, traffic light, traffic sign, train, rider
50
+
51
+ ### Dataset-specific Details:
52
+
53
+ **Berkeley DeepDrive (BDD) 100K Dataset:**
54
+ - 100,000+ driving images with diverse weather and lighting conditions
55
+ - Designed for autonomous driving applications
56
+ - Contains urban driving scenarios from multiple cities
57
+ - Annotations include bounding boxes for vehicles, pedestrians, and traffic elements
58
+
59
+ ## Usage
60
+
61
+ This model can be used with the Ultralytics YOLOv10 framework:
62
+
63
+ ```python
64
+ from ultralytics import YOLO
65
+
66
+ # Load the model
67
+ model = YOLO('path/to/best.pt')
68
+
69
+ # Run inference
70
+ results = model('path/to/image.jpg')
71
+
72
+ # Process results
73
+ for result in results:
74
+ boxes = result.boxes.xyxy # bounding boxes
75
+ scores = result.boxes.conf # confidence scores
76
+ classes = result.boxes.cls # class predictions
77
+ ```
78
+
79
+ ## Model Performance
80
+
81
+ This model was trained from scratch on the Berkeley DeepDrive (BDD) 100K dataset using YOLOv10 architecture.
82
+
83
+ ## Intended Use
84
+
85
+ - **Primary Use**: Object detection in autonomous driving scenarios
86
+ - **Suitable for**: Research, development, and deployment of object detection systems
87
+ - **Limitations**: Performance may vary on images significantly different from the training distribution
88
+
89
+ ## Citation
90
+
91
+ If you use this model, please cite:
92
+
93
+ ```bibtex
94
+ @article{yolov10,
95
+ title={YOLOv10: Real-Time End-to-End Object Detection},
96
+ author={Wang, Ao and Chen, Hui and Liu, Lihao and Chen, Kai and Lin, Zijia and Han, Jungong and Ding, Guiguang},
97
+ journal={arXiv preprint arXiv:2405.14458},
98
+ year={2024}
99
+ }
100
+ ```
101
+
102
+ ## License
103
+
104
+ This model is released under the MIT License.
105
+
106
+ ## Keywords
107
+
108
+ YOLOv10, Object Detection, Computer Vision, BDD 100K, Autonomous Driving, Deep Learning