|
|
--- |
|
|
license: agpl-3.0 |
|
|
tags: |
|
|
- object-detection |
|
|
- computer-vision |
|
|
- yolov10 |
|
|
datasets: |
|
|
- detection-datasets/coco |
|
|
inference: false |
|
|
--- |
|
|
|
|
|
### Model Description |
|
|
[YOLOv10: Real-Time End-to-End Object Detection](https://arxiv.org/abs/2405.14458v1) |
|
|
|
|
|
- arXiv: https://arxiv.org/abs/2405.14458v1 |
|
|
- github: https://github.com/THU-MIG/yolov10 |
|
|
|
|
|
### Installation |
|
|
``` |
|
|
pip install git+https://github.com/THU-MIG/yolov10.git supervision |
|
|
``` |
|
|
|
|
|
### Training/Validation |
|
|
```python |
|
|
from ultralytics import YOLOv10 |
|
|
|
|
|
model = YOLOv10.from_pretrained('jameslahm/yolov10n') |
|
|
# Training |
|
|
model.train(...) |
|
|
# after training, one can push to the hub |
|
|
model.push_to_hub("your-hf-username/yolov10-finetuned") |
|
|
|
|
|
# Validation |
|
|
model.val(...) |
|
|
|
|
|
# Prediction |
|
|
model.predict(...) |
|
|
``` |
|
|
|
|
|
### Inference |
|
|
|
|
|
Here's an end-to-end example showcasing inference on a cats image: |
|
|
|
|
|
```python |
|
|
from ultralytics import YOLOv10 |
|
|
import supervision as sv |
|
|
from PIL import Image |
|
|
import requests |
|
|
|
|
|
# load model |
|
|
model = YOLOv10.from_pretrained("nielsr/yolov10n") |
|
|
|
|
|
# load image |
|
|
url = 'http://images.cocodataset.org/val2017/000000039769.jpg' |
|
|
image = Image.open(requests.get(url, stream=True).raw) |
|
|
image = np.array(image) |
|
|
|
|
|
# perform inference |
|
|
results = model(source=image, conf=0.25, verbose=False)[0] |
|
|
detections = sv.Detections.from_ultralytics(results) |
|
|
box_annotator = sv.BoxAnnotator() |
|
|
|
|
|
category_dict = { |
|
|
0: 'person', 1: 'bicycle', 2: 'car', 3: 'motorcycle', 4: 'airplane', 5: 'bus', |
|
|
6: 'train', 7: 'truck', 8: 'boat', 9: 'traffic light', 10: 'fire hydrant', |
|
|
11: 'stop sign', 12: 'parking meter', 13: 'bench', 14: 'bird', 15: 'cat', |
|
|
16: 'dog', 17: 'horse', 18: 'sheep', 19: 'cow', 20: 'elephant', 21: 'bear', |
|
|
22: 'zebra', 23: 'giraffe', 24: 'backpack', 25: 'umbrella', 26: 'handbag', |
|
|
27: 'tie', 28: 'suitcase', 29: 'frisbee', 30: 'skis', 31: 'snowboard', |
|
|
32: 'sports ball', 33: 'kite', 34: 'baseball bat', 35: 'baseball glove', |
|
|
36: 'skateboard', 37: 'surfboard', 38: 'tennis racket', 39: 'bottle', |
|
|
40: 'wine glass', 41: 'cup', 42: 'fork', 43: 'knife', 44: 'spoon', 45: 'bowl', |
|
|
46: 'banana', 47: 'apple', 48: 'sandwich', 49: 'orange', 50: 'broccoli', |
|
|
51: 'carrot', 52: 'hot dog', 53: 'pizza', 54: 'donut', 55: 'cake', |
|
|
56: 'chair', 57: 'couch', 58: 'potted plant', 59: 'bed', 60: 'dining table', |
|
|
61: 'toilet', 62: 'tv', 63: 'laptop', 64: 'mouse', 65: 'remote', 66: 'keyboard', |
|
|
67: 'cell phone', 68: 'microwave', 69: 'oven', 70: 'toaster', 71: 'sink', |
|
|
72: 'refrigerator', 73: 'book', 74: 'clock', 75: 'vase', 76: 'scissors', |
|
|
77: 'teddy bear', 78: 'hair drier', 79: 'toothbrush' |
|
|
} |
|
|
|
|
|
labels = [ |
|
|
f"{category_dict[class_id]} {confidence:.2f}" |
|
|
for class_id, confidence in zip(detections.class_id, detections.confidence) |
|
|
] |
|
|
annotated_image = box_annotator.annotate( |
|
|
image.copy(), detections=detections, labels=labels |
|
|
) |
|
|
|
|
|
Image.fromarray(annotated_image) |
|
|
``` |
|
|
which shows: |
|
|
|
|
|
 |
|
|
|
|
|
### BibTeX Entry and Citation Info |
|
|
``` |
|
|
@article{wang2024yolov10, |
|
|
title={YOLOv10: Real-Time End-to-End Object Detection}, |
|
|
author={Wang, Ao and Chen, Hui and Liu, Lihao and Chen, Kai and Lin, Zijia and Han, Jungong and Ding, Guiguang}, |
|
|
journal={arXiv preprint arXiv:2405.14458}, |
|
|
year={2024} |
|
|
} |
|
|
``` |
