์ฝ˜ํ…์ธ ๋กœ ๊ฑด๋„ˆ๋›ฐ๊ธฐ

์ด๋ฏธ์ง€๋„ท ๋ฐ์ดํ„ฐ ์„ธํŠธ

ImageNet is a large-scale database of annotated images designed for use in visual object recognition research. It contains over 14 million images, with each image annotated using WordNet synsets, making it one of the most extensive resources available for training deep learning models in computer vision tasks.

ImageNet ์‚ฌ์ „ ํ•™์Šต ๋ชจ๋ธ

๋ชจ๋ธ ํฌ๊ธฐ
(ํ”ฝ์…€)
acc
top1
ACC
TOP5
์†๋„
CPU ONNX
(ms)
Speed
T4 TensorRT10
(ms)
๋งค๊ฐœ๋ณ€์ˆ˜
(M)
FLOPs
(B) at 640
YOLO11n-cls 224 70.0 89.4 5.0 ยฑ 0.3 1.1 ยฑ 0.0 1.6 3.3
YOLO11s-cls 224 75.4 92.7 7.9 ยฑ 0.2 1.3 ยฑ 0.0 5.5 12.1
YOLO11m-cls 224 77.3 93.9 17.2 ยฑ 0.4 2.0 ยฑ 0.0 10.4 39.3
YOLO11l-cls 224 78.3 94.3 23.2 ยฑ 0.3 2.8 ยฑ 0.0 12.9 49.4
YOLO11x-cls 224 79.5 94.9 41.4 ยฑ 0.9 3.8 ยฑ 0.0 28.4 110.4

์ฃผ์š” ๊ธฐ๋Šฅ

  • ์ด๋ฏธ์ง€๋„ท์—๋Š” ์ˆ˜์ฒœ ๊ฐœ์˜ ๊ฐœ์ฒด ์นดํ…Œ๊ณ ๋ฆฌ๋ฅผ ์•„์šฐ๋ฅด๋Š” 1,400๋งŒ ๊ฐœ ์ด์ƒ์˜ ๊ณ ํ•ด์ƒ๋„ ์ด๋ฏธ์ง€๊ฐ€ ํฌํ•จ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.
  • ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ์›Œ๋“œ๋„ท ๊ณ„์ธต ๊ตฌ์กฐ์— ๋”ฐ๋ผ ๊ตฌ์„ฑ๋˜๋ฉฐ, ๊ฐ ๋™์˜์–ด๋Š” ์นดํ…Œ๊ณ ๋ฆฌ๋ฅผ ๋‚˜ํƒ€๋ƒ…๋‹ˆ๋‹ค.
  • ImageNet is widely used for training and benchmarking in the field of computer vision, particularly for image classification and object detection tasks.
  • ๋งค๋…„ ์—ด๋ฆฌ๋Š” ILSVRC(ImageNet ๋Œ€๊ทœ๋ชจ ์‹œ๊ฐ ์ธ์‹ ์ฑŒ๋ฆฐ์ง€)๋Š” ์ปดํ“จํ„ฐ ๋น„์ „ ์—ฐ๊ตฌ๋ฅผ ๋ฐœ์ „์‹œํ‚ค๋Š” ๋ฐ ์ค‘์š”ํ•œ ์—ญํ• ์„ ํ•ด์™”์Šต๋‹ˆ๋‹ค.

๋ฐ์ดํ„ฐ ์„ธํŠธ ๊ตฌ์กฐ

์ด๋ฏธ์ง€๋„ท ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ์›Œ๋“œ๋„ท ๊ณ„์ธต๊ตฌ์กฐ๋ฅผ ์‚ฌ์šฉํ•ด ๊ตฌ์„ฑ๋ฉ๋‹ˆ๋‹ค. ๊ณ„์ธต ๊ตฌ์กฐ์˜ ๊ฐ ๋…ธ๋“œ๋Š” ์นดํ…Œ๊ณ ๋ฆฌ๋ฅผ ๋‚˜ํƒ€๋‚ด๋ฉฐ, ๊ฐ ์นดํ…Œ๊ณ ๋ฆฌ๋Š” ๋™์˜์–ด ๋ชจ์Œ์ธ ์‹ ์…‹(synset)์œผ๋กœ ์„ค๋ช…๋ฉ๋‹ˆ๋‹ค. ์ด๋ฏธ์ง€๋„ท์˜ ์ด๋ฏธ์ง€์—๋Š” ํ•˜๋‚˜ ์ด์ƒ์˜ ์‹ ์…‹์œผ๋กœ ์ฃผ์„์ด ์ถ”๊ฐ€๋˜์–ด ๋‹ค์–‘ํ•œ ๊ฐ์ฒด์™€ ๊ทธ ๊ด€๊ณ„๋ฅผ ์ธ์‹ํ•˜๊ธฐ ์œ„ํ•œ ํ›ˆ๋ จ ๋ชจ๋ธ์— ํ’๋ถ€ํ•œ ๋ฆฌ์†Œ์Šค๋ฅผ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค.

์ด๋ฏธ์ง€๋„ท ๋Œ€๊ทœ๋ชจ ์‹œ๊ฐ ์ธ์‹ ์ฑŒ๋ฆฐ์ง€(ILSVRC)

๋งค๋…„ ์—ด๋ฆฌ๋Š” ImageNet ๋Œ€๊ทœ๋ชจ ์‹œ๊ฐ ์ธ์‹ ์ฑŒ๋ฆฐ์ง€(ILSVRC) ๋Š” ์ปดํ“จํ„ฐ ๋น„์ „ ๋ถ„์•ผ์—์„œ ์ค‘์š”ํ•œ ํ–‰์‚ฌ์ž…๋‹ˆ๋‹ค. ์ด ํ–‰์‚ฌ๋Š” ์—ฐ๊ตฌ์ž์™€ ๊ฐœ๋ฐœ์ž๊ฐ€ ํ‘œ์ค€ํ™”๋œ ํ‰๊ฐ€ ์ง€ํ‘œ๋ฅผ ํ†ตํ•ด ๋Œ€๊ทœ๋ชจ ๋ฐ์ดํ„ฐ ์„ธํŠธ์—์„œ ์•Œ๊ณ ๋ฆฌ์ฆ˜๊ณผ ๋ชจ๋ธ์„ ํ‰๊ฐ€ํ•  ์ˆ˜ ์žˆ๋Š” ํ”Œ๋žซํผ์„ ์ œ๊ณตํ•ด ์™”์Šต๋‹ˆ๋‹ค. ILSVRC๋Š” ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜, ๋ฌผ์ฒด ๊ฐ์ง€ ๋ฐ ๊ธฐํƒ€ ์ปดํ“จํ„ฐ ๋น„์ „ ์ž‘์—…์„ ์œ„ํ•œ ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ ๊ฐœ๋ฐœ์—์„œ ์ƒ๋‹นํ•œ ๋ฐœ์ „์„ ์ด๋Œ์–ด๋ƒˆ์Šต๋‹ˆ๋‹ค.

์• ํ”Œ๋ฆฌ์ผ€์ด์…˜

์ด๋ฏธ์ง€๋„ท ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜, ๋ฌผ์ฒด ๊ฐ์ง€, ๋ฌผ์ฒด ์œ„์น˜ ํŒŒ์•… ๋“ฑ ๋‹ค์–‘ํ•œ ์ปดํ“จํ„ฐ ๋น„์ „ ์ž‘์—…์—์„œ ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๊ณ  ํ‰๊ฐ€ํ•˜๋Š” ๋ฐ ๋„๋ฆฌ ์‚ฌ์šฉ๋ฉ๋‹ˆ๋‹ค. AlexNet, VGG, ResNet๊ณผ ๊ฐ™์ด ๋„๋ฆฌ ์‚ฌ์šฉ๋˜๋Š” ๋”ฅ ๋Ÿฌ๋‹ ์•„ํ‚คํ…์ฒ˜๋Š” ImageNet ๋ฐ์ดํ„ฐ ์„ธํŠธ๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ๊ฐœ๋ฐœ๋˜๊ณ  ๋ฒค์น˜๋งˆํ‚น๋˜์—ˆ์Šต๋‹ˆ๋‹ค.

์‚ฌ์šฉ๋ฒ•

To train a deep learning model on the ImageNet dataset for 100 epochs with an image size of 224x224, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model Training page.

์—ด์ฐจ ์˜ˆ์‹œ

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="imagenet", epochs=100, imgsz=224)
# Start training from a pretrained *.pt model
yolo classify train data=imagenet model=yolo11n-cls.pt epochs=100 imgsz=224

์ƒ˜ํ”Œ ์ด๋ฏธ์ง€ ๋ฐ ์ฃผ์„

ImageNet ๋ฐ์ดํ„ฐ ์„ธํŠธ์—๋Š” ์ˆ˜์ฒœ ๊ฐœ์˜ ๋ฌผ์ฒด ์นดํ…Œ๊ณ ๋ฆฌ๋ฅผ ์•„์šฐ๋ฅด๋Š” ๊ณ ํ•ด์ƒ๋„ ์ด๋ฏธ์ง€๊ฐ€ ํฌํ•จ๋˜์–ด ์žˆ์–ด ์ปดํ“จํ„ฐ ๋น„์ „ ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๊ณ  ํ‰๊ฐ€ํ•  ์ˆ˜ ์žˆ๋Š” ๋‹ค์–‘ํ•˜๊ณ  ๊ด‘๋ฒ”์œ„ํ•œ ๋ฐ์ดํ„ฐ ์„ธํŠธ๋ฅผ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค. ๋‹ค์Œ์€ ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ์ด๋ฏธ์ง€ ๋ช‡ ๊ฐ€์ง€ ์˜ˆ์‹œ์ž…๋‹ˆ๋‹ค:

๋ฐ์ดํ„ฐ ์„ธํŠธ ์ƒ˜ํ”Œ ์ด๋ฏธ์ง€

์ด ์˜ˆ๋Š” ์ด๋ฏธ์ง€๋„ท ๋ฐ์ดํ„ฐ ์„ธํŠธ์— ํฌํ•จ๋œ ์ด๋ฏธ์ง€์˜ ๋‹ค์–‘์„ฑ๊ณผ ๋ณต์žก์„ฑ์„ ๋ณด์—ฌ์ฃผ๋ฉฐ, ๊ฐ•๋ ฅํ•œ ์ปดํ“จํ„ฐ ๋น„์ „ ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๋Š” ๋ฐ ์žˆ์–ด ๋‹ค์–‘ํ•œ ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ์ค‘์š”์„ฑ์„ ๊ฐ•์กฐํ•ฉ๋‹ˆ๋‹ค.

์ธ์šฉ ๋ฐ ๊ฐ์‚ฌ

์—ฐ๊ตฌ ๋˜๋Š” ๊ฐœ๋ฐœ ์ž‘์—…์— ImageNet ๋ฐ์ดํ„ฐ์…‹์„ ์‚ฌ์šฉํ•˜๋Š” ๊ฒฝ์šฐ ๋‹ค์Œ ๋…ผ๋ฌธ์„ ์ธ์šฉํ•ด ์ฃผ์„ธ์š”:

@article{ILSVRC15,
         author = {Olga Russakovsky and Jia Deng and Hao Su and Jonathan Krause and Sanjeev Satheesh and Sean Ma and Zhiheng Huang and Andrej Karpathy and Aditya Khosla and Michael Bernstein and Alexander C. Berg and Li Fei-Fei},
         title={ImageNet Large Scale Visual Recognition Challenge},
         year={2015},
         journal={International Journal of Computer Vision (IJCV)},
         volume={115},
         number={3},
         pages={211-252}
}

We would like to acknowledge the ImageNet team, led by Olga Russakovsky, Jia Deng, and Li Fei-Fei, for creating and maintaining the ImageNet dataset as a valuable resource for the machine learning and computer vision research community. For more information about the ImageNet dataset and its creators, visit the ImageNet website.

์ž์ฃผ ๋ฌป๋Š” ์งˆ๋ฌธ

์ด๋ฏธ์ง€๋„ท ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ๋ฌด์—‡์ด๋ฉฐ ์ปดํ“จํ„ฐ ๋น„์ „์—์„œ ์–ด๋–ป๊ฒŒ ์‚ฌ์šฉ๋˜๋‚˜์š”?

์ด๋ฏธ์ง€๋„ท ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ์›Œ๋“œ๋„ท ์‹ฑ์…‹์„ ์‚ฌ์šฉํ•ด ๋ถ„๋ฅ˜๋œ 1,400๋งŒ ๊ฐœ ์ด์ƒ์˜ ๊ณ ํ•ด์ƒ๋„ ์ด๋ฏธ์ง€๋กœ ๊ตฌ์„ฑ๋œ ๋Œ€๊ทœ๋ชจ ๋ฐ์ดํ„ฐ๋ฒ ์ด์Šค์ž…๋‹ˆ๋‹ค. ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜ ๋ฐ ๊ฐ์ฒด ๊ฐ์ง€๋ฅผ ํฌํ•จํ•œ ์‹œ๊ฐ์  ๊ฐ์ฒด ์ธ์‹ ์—ฐ๊ตฌ์— ๊ด‘๋ฒ”์œ„ํ•˜๊ฒŒ ์‚ฌ์šฉ๋ฉ๋‹ˆ๋‹ค. ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ์ฃผ์„๊ณผ ๋ฐฉ๋Œ€ํ•œ ์–‘์€ ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ ํ•™์Šต์„ ์œ„ํ•œ ํ’๋ถ€ํ•œ ๋ฆฌ์†Œ์Šค๋ฅผ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค. ํŠนํžˆ AlexNet, VGG, ResNet๊ณผ ๊ฐ™์€ ๋ชจ๋ธ์€ ImageNet์„ ์‚ฌ์šฉํ•˜์—ฌ ํ›ˆ๋ จ๋˜๊ณ  ๋ฒค์น˜๋งˆํ‚น๋˜์–ด ์ปดํ“จํ„ฐ ๋น„์ „์„ ๋ฐœ์ „์‹œํ‚ค๋Š” ๋ฐ ์žˆ์–ด ๊ทธ ์—ญํ• ์„ ๋ณด์—ฌ์ฃผ๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.

์ด๋ฏธ์ง€๋„ท ๋ฐ์ดํ„ฐ ์„ธํŠธ์—์„œ ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜๋ฅผ ์œ„ํ•ด ์‚ฌ์ „ ํ•™์Šต๋œ YOLO ๋ชจ๋ธ์„ ์‚ฌ์šฉํ•˜๋ ค๋ฉด ์–ด๋–ป๊ฒŒ ํ•ด์•ผ ํ•˜๋‚˜์š”?

์ด๋ฏธ์ง€๋„ท ๋ฐ์ดํ„ฐ ์„ธํŠธ์—์„œ ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜๋ฅผ ์œ„ํ•ด ์‚ฌ์ „ ํ•™์Šต๋œ Ultralytics YOLO ๋ชจ๋ธ์„ ์‚ฌ์šฉํ•˜๋ ค๋ฉด ๋‹ค์Œ ๋‹จ๊ณ„๋ฅผ ๋”ฐ๋ฅด์„ธ์š”:

์—ด์ฐจ ์˜ˆ์‹œ

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="imagenet", epochs=100, imgsz=224)
# Start training from a pretrained *.pt model
yolo classify train data=imagenet model=yolo11n-cls.pt epochs=100 imgsz=224

๋ณด๋‹ค ์‹ฌ์ธต์ ์ธ ๊ต์œก ์ง€์นจ์€ ๊ต์œก ํŽ˜์ด์ง€๋ฅผ ์ฐธ์กฐํ•˜์„ธ์š”.

Why should I use the Ultralytics YOLO11 pretrained models for my ImageNet dataset projects?

Ultralytics YOLO11 pretrained models offer state-of-the-art performance in terms of speed and accuracy for various computer vision tasks. For example, the YOLO11n-cls model, with a top-1 accuracy of 69.0% and a top-5 accuracy of 88.3%, is optimized for real-time applications. Pretrained models reduce the computational resources required for training from scratch and accelerate development cycles. Learn more about the performance metrics of YOLO11 models in the ImageNet Pretrained Models section.

์ด๋ฏธ์ง€๋„ท ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ์–ด๋–ป๊ฒŒ ๊ตฌ์กฐํ™”๋˜์–ด ์žˆ์œผ๋ฉฐ, ์ด๊ฒƒ์ด ์ค‘์š”ํ•œ ์ด์œ ๋Š” ๋ฌด์—‡์ธ๊ฐ€์š”?

์ด๋ฏธ์ง€๋„ท ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ์›Œ๋“œ๋„ท ๊ณ„์ธต ๊ตฌ์กฐ๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ๊ตฌ์„ฑ๋˜๋ฉฐ, ๊ณ„์ธต ๊ตฌ์กฐ์˜ ๊ฐ ๋…ธ๋“œ๋Š” ๋™์˜์–ด ์ง‘ํ•ฉ(๋™์˜์–ด ์šฉ์–ด์˜ ๋ชจ์Œ)์œผ๋กœ ์„ค๋ช…๋˜๋Š” ์นดํ…Œ๊ณ ๋ฆฌ๋ฅผ ๋‚˜ํƒ€๋ƒ…๋‹ˆ๋‹ค. ์ด ๊ตฌ์กฐ๋Š” ์ƒ์„ธํ•œ ์ฃผ์„์ด ๊ฐ€๋Šฅํ•˜๊ธฐ ๋•Œ๋ฌธ์— ๋‹ค์–‘ํ•œ ๊ฐ์ฒด๋ฅผ ์ธ์‹ํ•˜๋Š” ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๋Š” ๋ฐ ์ด์ƒ์ ์ž…๋‹ˆ๋‹ค. ์ด๋ฏธ์ง€๋„ท์˜ ๋‹ค์–‘์„ฑ๊ณผ ํ’๋ถ€ํ•œ ์ฃผ์„์€ ๊ฐ•๋ ฅํ•˜๊ณ  ์ผ๋ฐ˜ํ™” ๊ฐ€๋Šฅํ•œ ๋”ฅ ๋Ÿฌ๋‹ ๋ชจ๋ธ์„ ๊ฐœ๋ฐœํ•˜๋Š” ๋ฐ ์œ ์šฉํ•œ ๋ฐ์ดํ„ฐ ์„ธํŠธ์ž…๋‹ˆ๋‹ค. ์ด ์กฐ์ง์— ๋Œ€ํ•œ ์ž์„ธํ•œ ๋‚ด์šฉ์€ ๋ฐ์ดํ„ฐ ์„ธํŠธ ๊ตฌ์กฐ ์„น์…˜์—์„œ ํ™•์ธํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

์ด๋ฏธ์ง€๋„ท ๋Œ€๊ทœ๋ชจ ์‹œ๊ฐ ์ธ์‹ ์ฑŒ๋ฆฐ์ง€(ILSVRC)๋Š” ์ปดํ“จํ„ฐ ๋น„์ „์—์„œ ์–ด๋–ค ์—ญํ• ์„ ํ•˜๋‚˜์š”?

The annual ImageNet Large Scale Visual Recognition Challenge (ILSVRC) has been pivotal in driving advancements in computer vision by providing a competitive platform for evaluating algorithms on a large-scale, standardized dataset. It offers standardized evaluation metrics, fostering innovation and development in areas such as image classification, object detection, and image segmentation. The challenge has continuously pushed the boundaries of what is possible with deep learning and computer vision technologies.


๐Ÿ“… Created 11 months ago โœ๏ธ Updated 5 days ago

๋Œ“๊ธ€