์ฝ˜ํ…์ธ ๋กœ ๊ฑด๋„ˆ๋›ฐ๊ธฐ

์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜ ๋ฐ์ดํ„ฐ ์„ธํŠธ ๊ฐœ์š”

YOLO ๋ถ„๋ฅ˜ ์ž‘์—…์˜ ๋ฐ์ดํ„ฐ ์„ธํŠธ ๊ตฌ์กฐ

For Ultralytics YOLO ๋ถ„๋ฅ˜ ์ž‘์—…์˜ ๊ฒฝ์šฐ ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ์•„๋ž˜์˜ ํŠน์ • ๋ถ„ํ•  ๋””๋ ‰ํ„ฐ๋ฆฌ ๊ตฌ์กฐ๋กœ ๊ตฌ์„ฑ๋˜์–ด์•ผ ํ•ฉ๋‹ˆ๋‹ค. root ๋””๋ ‰ํ† ๋ฆฌ๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ์ ์ ˆํ•œ ๊ต์œก, ํ…Œ์ŠคํŠธ ๋ฐ ์„ ํƒ์  ์œ ํšจ์„ฑ ๊ฒ€์‚ฌ ํ”„๋กœ์„ธ์Šค๋ฅผ ์šฉ์ดํ•˜๊ฒŒ ํ•ฉ๋‹ˆ๋‹ค. ์ด ๊ตฌ์กฐ์—๋Š” ๊ต์œก์„ ์œ„ํ•œ ๋ณ„๋„์˜ ๋””๋ ‰ํ„ฐ๋ฆฌ(train) ๋ฐ ํ…Œ์ŠคํŠธ(test) ๋‹จ๊ณ„, ์œ ํšจ์„ฑ ๊ฒ€์‚ฌ๋ฅผ ์œ„ํ•œ ์„ ํƒ์  ๋””๋ ‰ํ† ๋ฆฌ(val).

์ด๋Ÿฌํ•œ ๊ฐ ๋””๋ ‰ํ„ฐ๋ฆฌ์—๋Š” ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ๊ฐ ํด๋ž˜์Šค์— ๋Œ€ํ•ด ํ•˜๋‚˜์˜ ํ•˜์œ„ ๋””๋ ‰ํ„ฐ๋ฆฌ๊ฐ€ ํฌํ•จ๋˜์–ด์•ผ ํ•ฉ๋‹ˆ๋‹ค. ํ•˜์œ„ ๋””๋ ‰ํ„ฐ๋ฆฌ๋Š” ํ•ด๋‹น ํด๋ž˜์Šค์˜ ์ด๋ฆ„์„ ๋”ฐ์„œ ๋ช…๋ช…๋˜๋ฉฐ ํ•ด๋‹น ํด๋ž˜์Šค์— ๋Œ€ํ•œ ๋ชจ๋“  ์ด๋ฏธ์ง€๋ฅผ ํฌํ•จํ•ฉ๋‹ˆ๋‹ค. ๊ฐ ์ด๋ฏธ์ง€ ํŒŒ์ผ์˜ ์ด๋ฆ„์€ ๊ณ ์œ ํ•˜๊ฒŒ ์ง€์ •ํ•˜๊ณ  JPEG ๋˜๋Š” PNG์™€ ๊ฐ™์€ ๊ณตํ†ต ํ˜•์‹์œผ๋กœ ์ €์žฅํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.

ํด๋” ๊ตฌ์กฐ ์˜ˆ์‹œ

CIFAR-10 ๋ฐ์ดํ„ฐ ์ง‘ํ•ฉ์„ ์˜ˆ๋กœ ๋“ค์–ด ๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค. ํด๋” ๊ตฌ์กฐ๋Š” ๋‹ค์Œ๊ณผ ๊ฐ™์•„์•ผ ํ•ฉ๋‹ˆ๋‹ค:

cifar-10-/
|
|-- train/
|   |-- airplane/
|   |   |-- 10008_airplane.png
|   |   |-- 10009_airplane.png
|   |   |-- ...
|   |
|   |-- automobile/
|   |   |-- 1000_automobile.png
|   |   |-- 1001_automobile.png
|   |   |-- ...
|   |
|   |-- bird/
|   |   |-- 10014_bird.png
|   |   |-- 10015_bird.png
|   |   |-- ...
|   |
|   |-- ...
|
|-- test/
|   |-- airplane/
|   |   |-- 10_airplane.png
|   |   |-- 11_airplane.png
|   |   |-- ...
|   |
|   |-- automobile/
|   |   |-- 100_automobile.png
|   |   |-- 101_automobile.png
|   |   |-- ...
|   |
|   |-- bird/
|   |   |-- 1000_bird.png
|   |   |-- 1001_bird.png
|   |   |-- ...
|   |
|   |-- ...
|
|-- val/ (optional)
|   |-- airplane/
|   |   |-- 105_airplane.png
|   |   |-- 106_airplane.png
|   |   |-- ...
|   |
|   |-- automobile/
|   |   |-- 102_automobile.png
|   |   |-- 103_automobile.png
|   |   |-- ...
|   |
|   |-- bird/
|   |   |-- 1045_bird.png
|   |   |-- 1046_bird.png
|   |   |-- ...
|   |
|   |-- ...

์ด๋Ÿฌํ•œ ๊ตฌ์กฐํ™”๋œ ์ ‘๊ทผ ๋ฐฉ์‹์€ ๋ชจ๋ธ์ด ํ›ˆ๋ จ ๋‹จ๊ณ„์—์„œ ์ž˜ ๊ตฌ์„ฑ๋œ ํด๋ž˜์Šค๋ฅผ ํ†ตํ•ด ํšจ๊ณผ์ ์œผ๋กœ ํ•™์Šตํ•˜๊ณ  ํ…Œ์ŠคํŠธ ๋ฐ ๊ฒ€์ฆ ๋‹จ๊ณ„์—์„œ ์„ฑ๋Šฅ์„ ์ •ํ™•ํ•˜๊ฒŒ ํ‰๊ฐ€ํ•  ์ˆ˜ ์žˆ๋„๋ก ํ•ฉ๋‹ˆ๋‹ค.

์‚ฌ์šฉ๋ฒ•

์˜ˆ

from ultralytics import YOLO

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

# Train the model
results = model.train(data="path/to/dataset", epochs=100, imgsz=640)
# Start training from a pretrained *.pt model
yolo detect train data=path/to/data model=yolo11n-cls.pt epochs=100 imgsz=640

์ง€์›๋˜๋Š” ๋ฐ์ดํ„ฐ ์„ธํŠธ

Ultralytics ๋Š” ์ž๋™ ๋‹ค์šด๋กœ๋“œ๋ฅผ ํ†ตํ•ด ๋‹ค์Œ๊ณผ ๊ฐ™์€ ๋ฐ์ดํ„ฐ ์„ธํŠธ๋ฅผ ์ง€์›ํ•ฉ๋‹ˆ๋‹ค:

  • Caltech 101: A dataset containing images of 101 object categories for image classification tasks.
  • Caltech 256: 256๊ฐœ์˜ ๊ฐœ์ฒด ๋ฒ”์ฃผ์™€ ๋” ์–ด๋ ค์šด ์ด๋ฏธ์ง€๊ฐ€ ํฌํ•จ๋œ Caltech 101์˜ ํ™•์žฅ ๋ฒ„์ „์ž…๋‹ˆ๋‹ค.
  • CIFAR-10: 10๊ฐœ์˜ ํด๋ž˜์Šค๋กœ ๊ตฌ์„ฑ๋œ 60K 32x32 ์ปฌ๋Ÿฌ ์ด๋ฏธ์ง€ ๋ฐ์ดํ„ฐ ์„ธํŠธ(ํด๋ž˜์Šค๋‹น 6K ์ด๋ฏธ์ง€)์ž…๋‹ˆ๋‹ค.
  • CIFAR-100: 100๊ฐœ์˜ ๊ฐ์ฒด ์นดํ…Œ๊ณ ๋ฆฌ์™€ ํด๋ž˜์Šค๋‹น 600๊ฐœ์˜ ์ด๋ฏธ์ง€๊ฐ€ ํฌํ•จ๋œ CIFAR-10์˜ ํ™•์žฅ ๋ฒ„์ „์ž…๋‹ˆ๋‹ค.
  • Fashion-MNIST: ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜ ์ž‘์—…์„ ์œ„ํ•œ 10๊ฐ€์ง€ ํŒจ์…˜ ์นดํ…Œ๊ณ ๋ฆฌ์˜ 70,000๊ฐœ ํ‘๋ฐฑ ์ด๋ฏธ์ง€๋กœ ๊ตฌ์„ฑ๋œ ๋ฐ์ดํ„ฐ ์„ธํŠธ์ž…๋‹ˆ๋‹ค.
  • ImageNet: A large-scale dataset for object detection and image classification with over 14 million images and 20,000 categories.
  • ImageNet-10: ๋” ๋น ๋ฅธ ์‹คํ—˜๊ณผ ํ…Œ์ŠคํŠธ๋ฅผ ์œ„ํ•ด 10๊ฐœ์˜ ์นดํ…Œ๊ณ ๋ฆฌ๋กœ ๊ตฌ์„ฑ๋œ ImageNet์˜ ์ž‘์€ ํ•˜์œ„ ์ง‘ํ•ฉ์ž…๋‹ˆ๋‹ค.
  • ์ด๋ฏธ์ง€๋„ท: ๋” ๋น ๋ฅธ ๊ต์œก๊ณผ ํ…Œ์ŠคํŠธ๋ฅผ ์œ„ํ•ด ์‰ฝ๊ฒŒ ๊ตฌ๋ถ„ํ•  ์ˆ˜ ์žˆ๋Š” 10๊ฐœ์˜ ํด๋ž˜์Šค๋ฅผ ํฌํ•จํ•˜๋Š” ImageNet์˜ ์ž‘์€ ํ•˜์œ„ ์ง‘ํ•ฉ์ž…๋‹ˆ๋‹ค.
  • ์ด๋ฏธ์ง€ ์šฐํ”„: ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜ ์ž‘์—…์„ ์œ„ํ•œ 10๊ฐ€์ง€ ๊ฒฌ์ข… ์นดํ…Œ๊ณ ๋ฆฌ๋ฅผ ํฌํ•จํ•˜๋Š” ImageNet์˜ ๋” ๊นŒ๋‹ค๋กœ์šด ํ•˜์œ„ ์ง‘ํ•ฉ์ž…๋‹ˆ๋‹ค.
  • MNIST: ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜ ์ž‘์—…์„ ์œ„ํ•œ 70,000๊ฐœ์˜ ์†์œผ๋กœ ์“ด ์ˆซ์ž๋กœ ๊ตฌ์„ฑ๋œ ํšŒ์ƒ‰์กฐ ์ด๋ฏธ์ง€ ๋ฐ์ดํ„ฐ ์„ธํŠธ์ž…๋‹ˆ๋‹ค.
  • MNIST160: First 8 images of each MNIST category from the MNIST dataset. Dataset contains 160 images total.

๋‚˜๋งŒ์˜ ๋ฐ์ดํ„ฐ ์ง‘ํ•ฉ ์ถ”๊ฐ€ํ•˜๊ธฐ

์ž์ฒด ๋ฐ์ดํ„ฐ ์„ธํŠธ๊ฐ€ ์žˆ๊ณ  ์ด๋ฅผ Ultralytics ๋กœ ๋ถ„๋ฅ˜ ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๋Š” ๋ฐ ์‚ฌ์šฉํ•˜๋ ค๋Š” ๊ฒฝ์šฐ, ์œ„์˜ "๋ฐ์ดํ„ฐ ์„ธํŠธ ํ˜•์‹"์—์„œ ์ง€์ •๋œ ํ˜•์‹์„ ๋”ฐ๋ฅด๋Š”์ง€ ํ™•์ธํ•œ ๋‹ค์Œ ๋‹ค์Œ์„ ๊ฐ€๋ฆฌํ‚ค์„ธ์š”. data ์ธ์ˆ˜๋ฅผ ๋ฐ์ดํ„ฐ ์ง‘ํ•ฉ ๋””๋ ‰ํ„ฐ๋ฆฌ์— ์ถ”๊ฐ€ํ•ฉ๋‹ˆ๋‹ค.

์ž์ฃผ ๋ฌป๋Š” ์งˆ๋ฌธ

YOLO ๋ถ„๋ฅ˜ ์ž‘์—…์„ ์œ„ํ•ด ๋ฐ์ดํ„ฐ ์ง‘ํ•ฉ์„ ์–ด๋–ป๊ฒŒ ๊ตฌ์„ฑํ•˜๋‚˜์š”?

Ultralytics YOLO ๋ถ„๋ฅ˜ ์ž‘์—…์„ ์œ„ํ•ด ๋ฐ์ดํ„ฐ ์ง‘ํ•ฉ์„ ๊ตฌ์„ฑํ•˜๋ ค๋ฉด ํŠน์ • ๋ถ„ํ•  ๋””๋ ‰ํ„ฐ๋ฆฌ ํ˜•์‹์„ ๋”ฐ๋ผ์•ผ ํ•ฉ๋‹ˆ๋‹ค. ๋ฐ์ดํ„ฐ ์ง‘ํ•ฉ์„ ๋‹ค์Œ๊ณผ ๊ฐ™์€ ๋ณ„๋„์˜ ๋””๋ ‰ํ„ฐ๋ฆฌ๋กœ ๊ตฌ์„ฑํ•ฉ๋‹ˆ๋‹ค. train, test๋ฐ ์„ ํƒ์ ์œผ๋กœ val. ์ด๋Ÿฌํ•œ ๊ฐ ๋””๋ ‰ํ„ฐ๋ฆฌ์—๋Š” ๊ฐ ํด๋ž˜์Šค์˜ ์ด๋ฆ„์„ ๋”ด ํ•˜์œ„ ๋””๋ ‰ํ„ฐ๋ฆฌ๊ฐ€ ์žˆ์–ด์•ผ ํ•˜๋ฉฐ, ๊ทธ ์•ˆ์— ํ•ด๋‹น ์ด๋ฏธ์ง€๊ฐ€ ๋“ค์–ด ์žˆ์–ด์•ผ ํ•ฉ๋‹ˆ๋‹ค. ์ด๋ ‡๊ฒŒ ํ•˜๋ฉด ๊ต์œก ๋ฐ ํ‰๊ฐ€ ํ”„๋กœ์„ธ์Šค๊ฐ€ ์›ํ™œํ•˜๊ฒŒ ์ง„ํ–‰๋ฉ๋‹ˆ๋‹ค. ์˜ˆ๋ฅผ ๋“ค์–ด CIFAR-10 ๋ฐ์ดํ„ฐ ์„ธํŠธ ํ˜•์‹์„ ์‚ดํŽด๋ด…์‹œ๋‹ค:

cifar-10-/
|-- train/
|   |-- airplane/
|   |-- automobile/
|   |-- bird/
|   ...
|-- test/
|   |-- airplane/
|   |-- automobile/
|   |-- bird/
|   ...
|-- val/ (optional)
|   |-- airplane/
|   |-- automobile/
|   |-- bird/
|   ...

์ž์„ธํ•œ ๋‚ด์šฉ์€ YOLO ๋ถ„๋ฅ˜ ์ž‘์—…์˜ ๋ฐ์ดํ„ฐ ์„ธํŠธ ๊ตฌ์กฐ๋ฅผ ์ฐธ์กฐํ•˜์„ธ์š”.

์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜๋ฅผ ์œ„ํ•ด Ultralytics YOLO ์—์„œ ์ง€์›ํ•˜๋Š” ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ๋ฌด์—‡์ธ๊ฐ€์š”?

Ultralytics YOLO ๋Š” ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜๋ฅผ ์œ„ํ•œ ์—ฌ๋Ÿฌ ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ์ž๋™ ๋‹ค์šด๋กœ๋“œ๋ฅผ ์ง€์›ํ•ฉ๋‹ˆ๋‹ค:

์ด๋Ÿฌํ•œ ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” YOLO ์—์„œ ์‰ฝ๊ฒŒ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ๋„๋ก ๊ตฌ์กฐํ™”๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค. ๊ฐ ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ํŽ˜์ด์ง€์—์„œ ๊ทธ ๊ตฌ์กฐ์™€ ํ™œ์šฉ์— ๋Œ€ํ•œ ์ž์„ธํ•œ ๋‚ด์šฉ์„ ํ™•์ธํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

YOLO ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜๋ฅผ ์œ„ํ•ด ๋‚˜๋งŒ์˜ ๋ฐ์ดํ„ฐ ์„ธํŠธ๋ฅผ ์ถ”๊ฐ€ํ•˜๋ ค๋ฉด ์–ด๋–ป๊ฒŒ ํ•ด์•ผ ํ•˜๋‚˜์š”?

์ž์ฒด ๋ฐ์ดํ„ฐ์…‹์„ ์‚ฌ์šฉํ•˜๋ ค๋ฉด Ultralytics YOLO , ๋ถ„๋ฅ˜ ์ž‘์—…์— ํ•„์š”ํ•œ ์ง€์ •๋œ ๋””๋ ‰ํ„ฐ๋ฆฌ ํ˜•์‹์„ ๋”ฐ๋ฅด๊ณ  ๋ณ„๋„์˜ train, test๋ฐ ์„ ํƒ์ ์œผ๋กœ val ๋””๋ ‰ํ„ฐ๋ฆฌ์™€ ๊ฐ ์ด๋ฏธ์ง€๊ฐ€ ํฌํ•จ๋œ ๊ฐ ํด๋ž˜์Šค์˜ ํ•˜์œ„ ๋””๋ ‰ํ„ฐ๋ฆฌ๋ฅผ ์ง€์ •ํ•ฉ๋‹ˆ๋‹ค. ๋ฐ์ดํ„ฐ ์„ธํŠธ๊ฐ€ ์˜ฌ๋ฐ”๋ฅด๊ฒŒ ๊ตฌ์กฐํ™”๋˜๋ฉด ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ data ์ธ์ˆ˜๋ฅผ ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ๋ฃจํŠธ ๋””๋ ‰ํ„ฐ๋ฆฌ์— ์ถ”๊ฐ€ํ•ฉ๋‹ˆ๋‹ค. ๋‹ค์Œ์€ Python ์— ์žˆ๋Š” ์˜ˆ์ œ์ž…๋‹ˆ๋‹ค:

from ultralytics import YOLO

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

# Train the model
results = model.train(data="path/to/your/dataset", epochs=100, imgsz=640)

์ž์„ธํ•œ ๋‚ด์šฉ์€ ๋‚˜๋งŒ์˜ ๋ฐ์ดํ„ฐ ์„ธํŠธ ์ถ”๊ฐ€ํ•˜๊ธฐ ์„น์…˜์—์„œ ํ™•์ธํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜์— Ultralytics YOLO ์„ ์‚ฌ์šฉํ•ด์•ผ ํ•˜๋Š” ์ด์œ ๋Š” ๋ฌด์—‡์ธ๊ฐ€์š”?

Ultralytics YOLO ๋Š” ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜์— ๋‹ค์Œ๊ณผ ๊ฐ™์€ ์—ฌ๋Ÿฌ ๊ฐ€์ง€ ์ด์ ์„ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค:

  • ์‚ฌ์ „ ํ•™์Šต๋œ ๋ชจ๋ธ: ๋‹ค์Œ๊ณผ ๊ฐ™์ด ์‚ฌ์ „ ํ•™์Šต๋œ ๋ชจ๋ธ์„ ๋กœ๋“œํ•ฉ๋‹ˆ๋‹ค. yolo11n-cls.pt ๋ฅผ ํด๋ฆญํ•ด ๊ต์œก ๊ณผ์ •์„ ์‹œ์ž‘ํ•˜์„ธ์š”.
  • ์‚ฌ์šฉ ํŽธ์˜์„ฑ: ๊ต์œก ๋ฐ ํ‰๊ฐ€๋ฅผ ์œ„ํ•œ ๊ฐ„๋‹จํ•œ API ๋ฐ CLI ๋ช…๋ น์–ด.
  • High Performance: State-of-the-art accuracy and speed, ideal for real-time applications.
  • ์—ฌ๋Ÿฌ ๋ฐ์ดํ„ฐ ์„ธํŠธ ์ง€์›: CIFAR-10, ImageNet ๋“ฑ ๋‹ค์–‘ํ•œ ์ธ๊ธฐ ๋ฐ์ดํ„ฐ ์„ธํŠธ์™€ ์›ํ™œํ•˜๊ฒŒ ํ†ตํ•ฉ๋ฉ๋‹ˆ๋‹ค.
  • ์ปค๋ฎค๋‹ˆํ‹ฐ ๋ฐ ์ง€์›: ๊ด‘๋ฒ”์œ„ํ•œ ๋ฌธ์„œ์™€ ๋ฌธ์ œ ํ•ด๊ฒฐ ๋ฐ ๊ฐœ์„ ์„ ์œ„ํ•œ ํ™œ๋ฐœํ•œ ์ปค๋ฎค๋‹ˆํ‹ฐ์— ์•ก์„ธ์Šคํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

์ถ”๊ฐ€ ์ธ์‚ฌ์ดํŠธ์™€ ์‹ค์ œ ์ ์šฉ ์‚ฌ๋ก€์— ๋Œ€ํ•œ ์ž์„ธํ•œ ๋‚ด์šฉ์€ Ultralytics YOLO.

Ultralytics YOLO ์„ ์‚ฌ์šฉํ•˜์—ฌ ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๋ ค๋ฉด ์–ด๋–ป๊ฒŒ ํ•ด์•ผ ํ•˜๋‚˜์š”?

Ultralytics YOLO ์„ ์‚ฌ์šฉํ•˜์—ฌ ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๋Š” ๊ฒƒ์€ Python ๊ณผ CLI ์—์„œ ๋ชจ๋‘ ์‰ฝ๊ฒŒ ์ˆ˜ํ–‰ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค:

์˜ˆ

from ultralytics import YOLO

# Load a model
model = YOLO("yolo11n-cls.pt")  # load a pretrained model

# Train the model
results = model.train(data="path/to/dataset", epochs=100, imgsz=640)
# Start training from a pretrained *.pt model
yolo detect train data=path/to/data model=yolo11n-cls.pt epochs=100 imgsz=640

์ด ์˜ˆ๋Š” ๋‘ ๊ฐ€์ง€ ์ ‘๊ทผ ๋ฐฉ์‹์„ ์‚ฌ์šฉํ•˜์—ฌ YOLO ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๋Š” ๊ฐ„๋‹จํ•œ ํ”„๋กœ์„ธ์Šค๋ฅผ ๋ณด์—ฌ์ค๋‹ˆ๋‹ค. ์ž์„ธํ•œ ๋‚ด์šฉ์€ ์‚ฌ์šฉ๋ฒ• ์„น์…˜์„ ์ฐธ์กฐํ•˜์„ธ์š”.


๐Ÿ“… Created 11 months ago โœ๏ธ Updated 1 day ago

๋Œ“๊ธ€