์ฝ˜ํ…์ธ ๋กœ ๊ฑด๋„ˆ๋›ฐ๊ธฐ

Roboflow ์œ ๋‹ˆ๋ฒ„์Šค ํฌ๋ž™ ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ

๊ท ์—ด ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” Roboflow ๊ท ์—ด ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ๊ตํ†ต ๋ฐ ๊ณต๊ณต ์•ˆ์ „ ์—ฐ๊ตฌ์— ์ข…์‚ฌํ•˜๋Š” ๊ฐœ์ธ์„ ์œ„ํ•ด ํŠน๋ณ„ํžˆ ๊ณ ์•ˆ๋œ ๊ด‘๋ฒ”์œ„ํ•œ ๋ฆฌ์†Œ์Šค๋กœ์„œ ๋‹๋ณด์ž…๋‹ˆ๋‹ค. ์ž์œจ ์ฃผํ–‰ ์ž๋™์ฐจ ๋ชจ๋ธ์„ ๊ฐœ๋ฐœํ•˜๊ฑฐ๋‚˜ ๋‹จ์ˆœํžˆ ์—ฌ๊ฐ€ ๋ชฉ์ ์œผ๋กœ ์ปดํ“จํ„ฐ ๋น„์ „ ์• ํ”Œ๋ฆฌ์ผ€์ด์…˜์„ ํƒ์ƒ‰ํ•˜๋Š” ์‚ฌ๋žŒ๋“ค์—๊ฒŒ๋„ ๋˜‘๊ฐ™์ด ์œ ์šฉํ•ฉ๋‹ˆ๋‹ค.

๋‹ค์–‘ํ•œ ๋„๋กœ ๋ฐ ๋ฒฝ๋ฉด ์‹œ๋‚˜๋ฆฌ์˜ค์—์„œ ์บก์ฒ˜ํ•œ ์ด 4029๊ฐœ์˜ ์ •์  ์ด๋ฏธ์ง€๋กœ ๊ตฌ์„ฑ๋œ ์ด ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ๊ท ์—ด ์„ธ๋ถ„ํ™”์™€ ๊ด€๋ จ๋œ ์ž‘์—…์— ์œ ์šฉํ•œ ์ž์‚ฐ์œผ๋กœ ๋ถ€์ƒํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. ๋ณต์žกํ•œ ๊ตํ†ต ์—ฐ๊ตฌ๋‚˜ ์ž์œจ์ฃผํ–‰์ฐจ ๋ชจ๋ธ์˜ ์ •ํ™•๋„๋ฅผ ๋†’์ด๊ณ ์ž ํ•˜๋Š” ๊ฒฝ์šฐ, ์ด ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ํ’๋ถ€ํ•˜๊ณ  ๋‹ค์–‘ํ•œ ์ด๋ฏธ์ง€ ๋ชจ์Œ์„ ์ œ๊ณตํ•˜์—ฌ ์—ฌ๋Ÿฌ๋ถ„์˜ ๋…ธ๋ ฅ์„ ์ง€์›ํ•ฉ๋‹ˆ๋‹ค.

๋ฐ์ดํ„ฐ ์„ธํŠธ ๊ตฌ์กฐ

ํฌ๋ž™ ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ ๋‚ด์˜ ๋ฐ์ดํ„ฐ ๋ถ„ํ• ์€ ๋‹ค์Œ๊ณผ ๊ฐ™์ด ์„ค๋ช…๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค:

  • ํŠธ๋ ˆ์ด๋‹ ์„ธํŠธ: 3717๊ฐœ์˜ ์ด๋ฏธ์ง€์™€ ํ•ด๋‹น ์ฃผ์„์œผ๋กœ ๊ตฌ์„ฑ๋ฉ๋‹ˆ๋‹ค.
  • ํ…Œ์ŠคํŠธ ์„ธํŠธ: 112๊ฐœ์˜ ์ด๋ฏธ์ง€์™€ ๊ฐ๊ฐ์˜ ์ฃผ์„์œผ๋กœ ๊ตฌ์„ฑ๋ฉ๋‹ˆ๋‹ค.
  • ์œ ํšจ์„ฑ ๊ฒ€์‚ฌ ์„ธํŠธ: 200๊ฐœ์˜ ์ด๋ฏธ์ง€์™€ ํ•ด๋‹น ์ฃผ์„์„ ํฌํ•จํ•ฉ๋‹ˆ๋‹ค.

์• ํ”Œ๋ฆฌ์ผ€์ด์…˜

๊ท ์—ด ์„ธ๋ถ„ํ™”๋Š” ์ธํ”„๋ผ ์œ ์ง€ ๋ณด์ˆ˜์— ์‹ค์šฉ์ ์œผ๋กœ ์ ์šฉ๋˜์–ด ๊ตฌ์กฐ์  ์†์ƒ์„ ์‹๋ณ„ํ•˜๊ณ  ํ‰๊ฐ€ํ•˜๋Š” ๋ฐ ๋„์›€์„ ์ค๋‹ˆ๋‹ค. ๋˜ํ•œ ์ž๋™ํ™”๋œ ์‹œ์Šคํ…œ์ด ํฌ์žฅ ๋„๋กœ์˜ ๊ท ์—ด์„ ๊ฐ์ง€ํ•˜๊ณ  ์ ์‹œ์— ์ˆ˜๋ฆฌํ•  ์ˆ˜ ์žˆ๋„๋ก ํ•˜์—ฌ ๋„๋กœ ์•ˆ์ „์„ ํ–ฅ์ƒ์‹œํ‚ค๋Š” ๋ฐ ์ค‘์š”ํ•œ ์—ญํ• ์„ ํ•ฉ๋‹ˆ๋‹ค.

๋ฐ์ดํ„ฐ ์„ธํŠธ YAML

๊ฒฝ๋กœ, ํด๋ž˜์Šค ๋ฐ ๊ธฐํƒ€ ๊ด€๋ จ ์ •๋ณด์— ๋Œ€ํ•œ ์„ธ๋ถ€ ์ •๋ณด๋ฅผ ํฌํ•จํ•˜๋Š” ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ๊ตฌ์„ฑ์„ ์„ค๋ช…ํ•˜๊ธฐ ์œ„ํ•ด YAML(๋˜ ๋‹ค๋ฅธ ๋งˆํฌ์—… ์–ธ์–ด) ํŒŒ์ผ์ด ์‚ฌ์šฉ๋ฉ๋‹ˆ๋‹ค. ํŠนํžˆ, ํฌ๋ž™ ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ๊ฒฝ์šฐ์—๋Š” crack-seg.yaml ํŒŒ์ผ์€ ๋‹ค์Œ์—์„œ ๊ด€๋ฆฌ ๋ฐ ์•ก์„ธ์Šค ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/crack-seg.yaml.

ultralytics/cfg/datasets/crack-seg.yaml

# Ultralytics YOLO ๐Ÿš€, AGPL-3.0 license
# Crack-seg dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/segment/crack-seg/
# Example usage: yolo train data=crack-seg.yaml
# parent
# โ”œโ”€โ”€ ultralytics
# โ””โ”€โ”€ datasets
#     โ””โ”€โ”€ crack-seg  โ† downloads here (91.2 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/crack-seg # dataset root dir
train: train/images # train images (relative to 'path') 3717 images
val: valid/images # val images (relative to 'path') 112 images
test: test/images # test images (relative to 'path') 200 images

# Classes
names:
  0: crack

# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/crack-seg.zip

์‚ฌ์šฉ๋ฒ•

์ด๋ฏธ์ง€ ํฌ๊ธฐ๊ฐ€ 640์ธ 100๊ฐœ์˜ ์—ํฌํฌ์— ๋Œ€ํ•œ ๊ท ์—ด ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ์—์„œ Ultralytics YOLO11n ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๋ ค๋ฉด ๋‹ค์Œ ์ฝ”๋“œ ์กฐ๊ฐ์„ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ์‚ฌ์šฉ ๊ฐ€๋Šฅํ•œ ์ธ์ˆ˜์˜ ์ „์ฒด ๋ชฉ๋ก์€ ๋ชจ๋ธ ํ•™์Šต ํŽ˜์ด์ง€๋ฅผ ์ฐธ์กฐํ•˜์„ธ์š”.

์—ด์ฐจ ์˜ˆ์‹œ

from ultralytics import YOLO

# Load a model
model = YOLO("yolo11n-seg.pt")  # load a pretrained model (recommended for training)

# Train the model
results = model.train(data="crack-seg.yaml", epochs=100, imgsz=640)
# Start training from a pretrained *.pt model
yolo segment train data=crack-seg.yaml model=yolo11n-seg.pt epochs=100 imgsz=640

์ƒ˜ํ”Œ ๋ฐ์ดํ„ฐ ๋ฐ ์ฃผ์„

๊ท ์—ด ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ๋‹ค์–‘ํ•œ ๊ด€์ ์—์„œ ์บก์ฒ˜ํ•œ ๋‹ค์–‘ํ•œ ์ด๋ฏธ์ง€์™€ ๋น„๋””์˜ค ๋ชจ์Œ์œผ๋กœ ๊ตฌ์„ฑ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค. ์•„๋ž˜๋Š” ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ๋ฐ์ดํ„ฐ ์ธ์Šคํ„ด์Šค์™€ ๊ฐ๊ฐ์˜ ์ฃผ์„์ž…๋‹ˆ๋‹ค:

๋ฐ์ดํ„ฐ ์„ธํŠธ ์ƒ˜ํ”Œ ์ด๋ฏธ์ง€

  • ์ด ์ด๋ฏธ์ง€๋Š” ์ด๋ฏธ์ง€ ๊ฐ์ฒด ๋ถ„ํ• ์˜ ์˜ˆ๋ฅผ ๋ณด์—ฌ์ฃผ๋Š” ๊ฒƒ์œผ๋กœ, ์‹๋ณ„๋œ ๊ฐ์ฒด์˜ ์œค๊ณฝ์„ ๋‚˜ํƒ€๋‚ด๋Š” ๋งˆ์Šคํฌ๊ฐ€ ์žˆ๋Š” ์ฃผ์„์ด ๋‹ฌ๋ฆฐ ๊ฒฝ๊ณ„ ์ƒ์ž๊ฐ€ ํŠน์ง•์ž…๋‹ˆ๋‹ค. ์ด ๋ฐ์ดํ„ฐ ์„ธํŠธ์—๋Š” ๋‹ค์–‘ํ•œ ์œ„์น˜, ํ™˜๊ฒฝ, ๋ฐ€๋„์—์„œ ์ดฌ์˜๋œ ๋‹ค์–‘ํ•œ ์ด๋ฏธ์ง€๊ฐ€ ํฌํ•จ๋˜์–ด ์žˆ์–ด ์ด ํŠน์ • ์ž‘์—…์„ ์œ„ํ•ด ์„ค๊ณ„๋œ ๋ชจ๋ธ์„ ๊ฐœ๋ฐœํ•  ์ˆ˜ ์žˆ๋Š” ํฌ๊ด„์ ์ธ ๋ฆฌ์†Œ์Šค์ž…๋‹ˆ๋‹ค.

  • ์ด ์˜ˆ๋Š” ๊ท ์—ด ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ์—์„œ ๋ฐœ๊ฒฌ๋˜๋Š” ๋‹ค์–‘์„ฑ๊ณผ ๋ณต์žก์„ฑ์„ ๊ฐ•์กฐํ•˜๋ฉฐ ์ปดํ“จํ„ฐ ๋น„์ „ ์ž‘์—…์—์„œ ๊ณ ํ’ˆ์งˆ ๋ฐ์ดํ„ฐ์˜ ์ค‘์š”ํ•œ ์—ญํ• ์„ ๊ฐ•์กฐํ•ฉ๋‹ˆ๋‹ค.

์ธ์šฉ ๋ฐ ๊ฐ์‚ฌ

ํฌ๋ž™ ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ๋ฅผ ์—ฐ๊ตฌ ๋˜๋Š” ๊ฐœ๋ฐœ ์ž‘์—…์— ํ†ตํ•ฉํ•˜๋Š” ๊ฒฝ์šฐ ๋‹ค์Œ ๋ฌธ์„œ๋ฅผ ์ฐธ์กฐํ•˜์‹œ๊ธฐ ๋ฐ”๋ž๋‹ˆ๋‹ค:

@misc{ crack-bphdr_dataset,
    title = { crack Dataset },
    type = { Open Source Dataset },
    author = { University },
    howpublished = { \url{ https://universe.roboflow.com/university-bswxt/crack-bphdr } },
    url = { https://universe.roboflow.com/university-bswxt/crack-bphdr },
    journal = { Roboflow Universe },
    publisher = { Roboflow },
    year = { 2022 },
    month = { dec },
    note = { visited on 2024-01-23 },
}

๋„๋กœ ์•ˆ์ „ ๋ฐ ์—ฐ๊ตฌ ํ”„๋กœ์ ํŠธ๋ฅผ ์œ„ํ•œ ๊ท€์ค‘ํ•œ ๋ฆฌ์†Œ์Šค์ธ ๊ท ์—ด ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ๋ฅผ ๋งŒ๋“ค๊ณ  ์œ ์ง€ ๊ด€๋ฆฌํ•˜๋Š” Roboflow ํŒ€์— ๊ฐ์‚ฌ์˜ ๋ง์”€์„ ์ „ํ•ฉ๋‹ˆ๋‹ค. ๊ท ์—ด ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ์™€ ์ œ์ž‘์ž์— ๋Œ€ํ•œ ์ž์„ธํ•œ ๋‚ด์šฉ์€ ๊ท ์—ด ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ ํŽ˜์ด์ง€๋ฅผ ์ฐธ์กฐํ•˜์„ธ์š”.

์ž์ฃผ ๋ฌป๋Š” ์งˆ๋ฌธ

Roboflow ํฌ๋ž™ ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ๋ž€ ๋ฌด์—‡์ธ๊ฐ€์š”?

Roboflow ๊ท ์—ด ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ๊ตํ†ต ๋ฐ ๊ณต๊ณต ์•ˆ์ „ ์—ฐ๊ตฌ๋ฅผ ์œ„ํ•ด ํŠน๋ณ„ํžˆ ์„ค๊ณ„๋œ 4029๊ฐœ์˜ ์ •์  ์ด๋ฏธ์ง€๋กœ ๊ตฌ์„ฑ๋œ ํฌ๊ด„์ ์ธ ์ปฌ๋ ‰์…˜์ž…๋‹ˆ๋‹ค. ์ž์œจ์ฃผํ–‰์ฐจ ๋ชจ๋ธ ๊ฐœ๋ฐœ ๋ฐ ์ธํ”„๋ผ ์œ ์ง€ ๋ณด์ˆ˜์™€ ๊ฐ™์€ ์ž‘์—…์— ์ด์ƒ์ ์ž…๋‹ˆ๋‹ค. ์ด ๋ฐ์ดํ„ฐ ์„ธํŠธ์—๋Š” ํ›ˆ๋ จ, ํ…Œ์ŠคํŠธ, ๊ฒ€์ฆ ์„ธํŠธ๊ฐ€ ํฌํ•จ๋˜์–ด ์žˆ์–ด ์ •ํ™•ํ•œ ๊ท ์—ด ๊ฐ์ง€ ๋ฐ ์„ธ๋ถ„ํ™”๋ฅผ ์ง€์›ํ•ฉ๋‹ˆ๋‹ค.

๊ท ์—ด ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ( Ultralytics YOLO11 )๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๋ ค๋ฉด ์–ด๋–ป๊ฒŒ ํ•ด์•ผ ํ•˜๋‚˜์š”?

๊ท ์—ด ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ์—์„œ Ultralytics YOLO11 ๋ชจ๋ธ์„ ํ•™์Šตํ•˜๋ ค๋ฉด ๋‹ค์Œ ์ฝ”๋“œ ์กฐ๊ฐ์„ ์‚ฌ์šฉํ•˜์„ธ์š”. ์ž์„ธํ•œ ์ง€์นจ๊ณผ ์ถ”๊ฐ€ ๋งค๊ฐœ๋ณ€์ˆ˜๋Š” ๋ชจ๋ธ ํ›ˆ๋ จ ํŽ˜์ด์ง€์—์„œ ํ™•์ธํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

์—ด์ฐจ ์˜ˆ์‹œ

from ultralytics import YOLO

# Load a model
model = YOLO("yolo11n-seg.pt")  # load a pretrained model (recommended for training)

# Train the model
results = model.train(data="crack-seg.yaml", epochs=100, imgsz=640)
# Start training from a pretrained *.pt model
yolo segment train data=crack-seg.yaml model=yolo11n-seg.pt epochs=100 imgsz=640

์ž์œจ์ฃผํ–‰์ฐจ ํ”„๋กœ์ ํŠธ์— ํฌ๋ž™ ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ์„ธํŠธ๋ฅผ ์‚ฌ์šฉํ•ด์•ผ ํ•˜๋Š” ์ด์œ ๋Š” ๋ฌด์—‡์ธ๊ฐ€์š”?

๊ท ์—ด ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ๋‹ค์–‘ํ•œ ์‹œ๋‚˜๋ฆฌ์˜ค๋ฅผ ์ œ๊ณตํ•˜๋Š” 4029๊ฐœ์˜ ๋„๋กœ ๋ฐ ๋ฒฝ ์ด๋ฏธ์ง€๊ฐ€ ๋‹ค์–‘ํ•˜๊ฒŒ ์ˆ˜์ง‘๋˜์–ด ์žˆ์–ด ์ž์œจ์ฃผํ–‰์ฐจ ํ”„๋กœ์ ํŠธ์— ๋งค์šฐ ์ ํ•ฉํ•ฉ๋‹ˆ๋‹ค. ์ด๋Ÿฌํ•œ ๋‹ค์–‘์„ฑ์€ ๊ท ์—ด ๊ฐ์ง€๋ฅผ ์œ„ํ•ด ํ›ˆ๋ จ๋œ ๋ชจ๋ธ์˜ ์ •ํ™•์„ฑ๊ณผ ๊ฒฌ๊ณ ์„ฑ์„ ํ–ฅ์ƒ์‹œ์ผœ ๋„๋กœ ์•ˆ์ „์„ ์œ ์ง€ํ•˜๊ณ  ์ธํ”„๋ผ๋ฅผ ์ ์‹œ์— ์ˆ˜๋ฆฌํ•˜๋Š” ๋ฐ ๋งค์šฐ ์ค‘์š”ํ•ฉ๋‹ˆ๋‹ค.

Ultralytics YOLO ์€ ํฌ๋ž™ ์„ธ๋ถ„ํ™”๋ฅผ ์œ„ํ•ด ์–ด๋–ค ๊ณ ์œ ํ•œ ๊ธฐ๋Šฅ์„ ์ œ๊ณตํ•˜๋‚˜์š”?

Ultralytics YOLO ๋Š” ๊ณ ๊ธ‰ ์‹ค์‹œ๊ฐ„ ๊ฐœ์ฒด ๊ฐ์ง€, ์„ธ๋ถ„ํ™” ๋ฐ ๋ถ„๋ฅ˜ ๊ธฐ๋Šฅ์„ ์ œ๊ณตํ•˜์—ฌ ํฌ๋ž™ ์„ธ๋ถ„ํ™” ์ž‘์—…์— ์ด์ƒ์ ์ž…๋‹ˆ๋‹ค. ๋Œ€๊ทœ๋ชจ ๋ฐ์ดํ„ฐ ์„ธํŠธ์™€ ๋ณต์žกํ•œ ์‹œ๋‚˜๋ฆฌ์˜ค๋ฅผ ์ฒ˜๋ฆฌํ•  ์ˆ˜ ์žˆ์–ด ๋†’์€ ์ •ํ™•๋„์™€ ํšจ์œจ์„ฑ์„ ๋ณด์žฅํ•ฉ๋‹ˆ๋‹ค. ์˜ˆ๋ฅผ ๋“ค์–ด, ๋ชจ๋ธ ํ›ˆ๋ จ, ์˜ˆ์ธก ๋ฐ ๋‚ด๋ณด๋‚ด๊ธฐ ๋ชจ๋“œ๋Š” ํ›ˆ๋ จ๋ถ€ํ„ฐ ๋ฐฐํฌ๊นŒ์ง€ ํฌ๊ด„์ ์ธ ๊ธฐ๋Šฅ์„ ๋‹ค๋ฃน๋‹ˆ๋‹ค.

์—ฐ๊ตฌ ๋…ผ๋ฌธ์—์„œ Roboflow ํฌ๋ž™ ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ์…‹์„ ์ธ์šฉํ•˜๋ ค๋ฉด ์–ด๋–ป๊ฒŒ ํ•ด์•ผ ํ•˜๋‚˜์š”?

ํฌ๋ž™ ์„ธ๋ถ„ํ™” ๋ฐ์ดํ„ฐ์„ธํŠธ๋ฅผ ์—ฐ๊ตฌ์— ํ†ตํ•ฉํ•˜๋Š” ๊ฒฝ์šฐ ๋‹ค์Œ BibTeX ์ฐธ์กฐ๋ฅผ ์‚ฌ์šฉํ•˜์‹œ๊ธฐ ๋ฐ”๋ž๋‹ˆ๋‹ค:

@misc{ crack-bphdr_dataset,
    title = { crack Dataset },
    type = { Open Source Dataset },
    author = { University },
    howpublished = { \url{ https://universe.roboflow.com/university-bswxt/crack-bphdr } },
    url = { https://universe.roboflow.com/university-bswxt/crack-bphdr },
    journal = { Roboflow Universe },
    publisher = { Roboflow },
    year = { 2022 },
    month = { dec },
    note = { visited on 2024-01-23 },
}

์ด ์ธ์šฉ ํ˜•์‹์€ ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ์ œ์ž‘์ž์—๊ฒŒ ์ ์ ˆํ•œ ์ธ์ฆ์„ ๋ณด์žฅํ•˜๊ณ  ์—ฐ๊ตฌ์— ๋ฐ์ดํ„ฐ ์„ธํŠธ๊ฐ€ ์‚ฌ์šฉ๋˜์—ˆ์Œ์„ ์ธ์ •ํ•ฉ๋‹ˆ๋‹ค.

10๊ฐœ์›” ์ „ ์ƒ์„ฑ๋จ โœ๏ธ 2๊ฐœ์›” ์ „ ์—…๋ฐ์ดํŠธ๋จ

๋Œ“๊ธ€