COCO8-Seg λ°μ΄ν° μΈνΈ
μκ°
Ultralytics COCO8-Seg is a small, but versatile instance segmentation dataset composed of the first 8 images of the COCO train 2017 set, 4 for training and 4 for validation. This dataset is ideal for testing and debugging segmentation models, or for experimenting with new detection approaches. With 8 images, it is small enough to be easily manageable, yet diverse enough to test training pipelines for errors and act as a sanity check before training larger datasets.
This dataset is intended for use with Ultralytics HUB and YOLO11.
λ°μ΄ν° μΈνΈ YAML
λ°μ΄ν° μΈνΈ ꡬμ±μ μ μνλ λ°λ YAML(λ λ€λ₯Έ λ§ν¬μ
μΈμ΄) νμΌμ΄ μ¬μ©λ©λλ€. μ¬κΈ°μλ λ°μ΄ν° μΈνΈμ κ²½λ‘, ν΄λμ€ λ° κΈ°ν κ΄λ ¨ μ 보μ λν μ λ³΄κ° ν¬ν¨λμ΄ μμ΅λλ€. COCO8-Seg λ°μ΄ν° μΈνΈμ κ²½μ°, λ°μ΄ν° μΈνΈμ coco8-seg.yaml
νμΌμ λ€μ μμΉμμ μ μ§λ©λλ€. https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/coco8-seg.yaml.
ultralytics/cfg/datasets/coco8-seg.yaml
# Ultralytics YOLO π, AGPL-3.0 license
# COCO8-seg dataset (first 8 images from COCO train2017) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/segment/coco8-seg/
# Example usage: yolo train data=coco8-seg.yaml
# parent
# βββ ultralytics
# βββ datasets
# βββ coco8-seg β downloads here (1 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/coco8-seg # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images
test: # test images (optional)
# Classes
names:
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
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8-seg.zip
μ¬μ©λ²
To train a YOLO11n-seg model on the COCO8-Seg dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model Training page.
μ΄μ°¨ μμ
μν μ΄λ―Έμ§ λ° μ£Όμ
λ€μμ COCO8-Seg λ°μ΄ν° μΈνΈμ μ΄λ―Έμ§μ ν΄λΉ μ£Όμμ λͺ κ°μ§ μμμ λλ€:
- λͺ¨μμ΄ν¬ μ΄λ―Έμ§: μ΄ μ΄λ―Έμ§λ λͺ¨μμ΄ν¬λ λ°μ΄ν° μΈνΈ μ΄λ―Έμ§λ‘ ꡬμ±λ νλ ¨ λ°°μΉμ μμμ λλ€. λͺ¨μμ΄ν¬λ μ¬λ¬ μ΄λ―Έμ§λ₯Ό νλμ μ΄λ―Έμ§λ‘ κ²°ν©νμ¬ κ° νλ ¨ λ°°μΉ λ΄μμ λ€μν κ°μ²΄μ μ₯λ©΄μ λ리기 μν΄ νλ ¨ μ€μ μ¬μ©λλ κΈ°μ μ λλ€. μ΄λ₯Ό ν΅ν΄ λ€μν κ°μ²΄ ν¬κΈ°, μ’ ν‘λΉ λ° μ»¨ν μ€νΈμ μΌλ°ννλ λͺ¨λΈμ λ₯λ ₯μ ν₯μμν¬ μ μμ΅λλ€.
μ΄ μλ COCO8-Seg λ°μ΄ν° μΈνΈμ ν¬ν¨λ μ΄λ―Έμ§μ λ€μμ±κ³Ό 볡μ‘μ±, κ·Έλ¦¬κ³ νμ΅ κ³Όμ μμ λͺ¨μμ΄ν¬ μ¬μ©μ μ΄μ μ 보μ¬μ€λλ€.
μΈμ© λ° κ°μ¬
μ°κ΅¬ λλ κ°λ° μμ μ COCO λ°μ΄ν°μ μ μ¬μ©νλ κ²½μ° λ€μ λ Όλ¬Έμ μΈμ©ν΄ μ£ΌμΈμ:
@misc{lin2015microsoft,
title={Microsoft COCO: Common Objects in Context},
author={Tsung-Yi Lin and Michael Maire and Serge Belongie and Lubomir Bourdev and Ross Girshick and James Hays and Pietro Perona and Deva Ramanan and C. Lawrence Zitnick and Piotr DollΓ‘r},
year={2015},
eprint={1405.0312},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
We would like to acknowledge the COCO Consortium for creating and maintaining this valuable resource for the computer vision community. For more information about the COCO dataset and its creators, visit the COCO dataset website.
μμ£Ό 묻λ μ§λ¬Έ
What is the COCO8-Seg dataset, and how is it used in Ultralytics YOLO11?
The COCO8-Seg dataset is a compact instance segmentation dataset by Ultralytics, consisting of the first 8 images from the COCO train 2017 setβ4 images for training and 4 for validation. This dataset is tailored for testing and debugging segmentation models or experimenting with new detection methods. It is particularly useful with Ultralytics YOLO11 and HUB for rapid iteration and pipeline error-checking before scaling to larger datasets. For detailed usage, refer to the model Training page.
How can I train a YOLO11n-seg model using the COCO8-Seg dataset?
To train a YOLO11n-seg model on the COCO8-Seg dataset for 100 epochs with an image size of 640, you can use Python or CLI commands. Here's a quick example:
μ΄μ°¨ μμ
μ¬μ© κ°λ₯ν μΈμ λ° κ΅¬μ± μ΅μ μ λν μμΈν μ€λͺ μ κ΅μ‘ λ¬Έμλ₯Ό μ°Έμ‘°νμΈμ.
COCO8-Seg λ°μ΄ν° μΈνΈκ° λͺ¨λΈ κ°λ°κ³Ό λλ²κΉ μ μ€μν μ΄μ λ 무μμΈκ°μ?
COCO8-Seg λ°μ΄ν° μΈνΈλ μμ ν¬κΈ°μμ κ΄λ¦¬μ±κ³Ό λ€μμ±μ μ 곡νλ λ° μ΄μμ μ λλ€. λ¨ 8κ°μ μ΄λ―Έμ§λ‘ ꡬμ±λμ΄ μμ΄ λκ·λͺ¨ λ°μ΄ν° μΈνΈμ μ€λ²ν€λ μμ΄ μΈλΆν λͺ¨λΈμ΄λ μλ‘μ΄ νμ§ μ κ·Όλ²μ λΉ λ₯΄κ² ν μ€νΈνκ³ λλ²κΉ ν μ μμ΅λλ€. λ°λΌμ λκ·λͺ¨ λ°μ΄ν° μΈνΈμ λν κ΄λ²μν νμ΅μ μ§ννκΈ° μ μ 건μ μ± κ²μ¬ λ° νμ΄νλΌμΈ μ€λ₯ μλ³μ μν ν¨μ¨μ μΈ λκ΅¬λ‘ μ¬μ©ν μ μμ΅λλ€. μ¬κΈ°μμ λ°μ΄ν° μΈνΈ νμμ λν΄ μμΈν μμ보μΈμ.
COCO8-Seg λ°μ΄ν° μΈνΈμ YAML κ΅¬μ± νμΌμ μ΄λμμ μ°Ύμ μ μλμ?
COCO8-Seg λ°μ΄ν° μΈνΈμ λν YAML κ΅¬μ± νμΌμ Ultralytics 리ν¬μ§ν 리μμ νμΈν μ μμ΅λλ€. μ¬κΈ°μμ μ§μ νμΌμ μ‘μΈμ€ν μ μμ΅λλ€. YAML νμΌμλ λͺ¨λΈ νμ΅ λ° μ ν¨μ± κ²μ¬μ νμν λ°μ΄ν° μΈνΈ κ²½λ‘, ν΄λμ€ λ° κ΅¬μ± μ€μ μ λν νμ μ λ³΄κ° ν¬ν¨λμ΄ μμ΅λλ€.
COCO8-Seg λ°μ΄ν° μΈνΈλ‘ νλ ¨ν λ λͺ¨μμ΄νΉμ μ¬μ©νλ©΄ μ΄λ€ μ΄μ μ΄ μλμ?
Using mosaicing during training helps increase the diversity and variety of objects and scenes in each training batch. This technique combines multiple images into a single composite image, enhancing the model's ability to generalize to different object sizes, aspect ratios, and contexts within the scene. Mosaicing is beneficial for improving a model's robustness and accuracy, especially when working with small datasets like COCO8-Seg. For an example of mosaiced images, see the Sample Images and Annotations section.