The ImageNet project is a large visual database designed for use in visual object recognition software research. More than 14 million images have been hand-annotated by the project to indicate what objects are pictured and in at least one million of the images, bounding boxes are also provided. (https://en.wikipedia.org/wiki/ImageNet)

이를 Classification하는 ILSVRC (ImageNet Large Scale Visual Recognition Challenge) 라는 경진대회가 있었다. 1000개 카테고리의 수백만 이미지로 구성됨.

다음과 같은 모델들이 알려짐

• VGG16: 533MB
• VGG19: 574MB
• ResNet: 102MB
• Inception V3 (GoogLeNet): 93MB
• Xception: 91MB

관련정보

• CNN- Imagenet에 쓰인 주요 모델 2018-01-26

Suggested Pages #

• 0.025 Deep learning
• 0.025 Receiver operating characteristic
• 0.025 Naive Bayes classifier
• 0.025 OpenCV
• 0.025 April 13
• 0.025 Fisher's linear discriminant
• 0.025 Artificial neural network
• 0.025 Binary classification
• 0.025 Python
• 0.025 September 3
• More suggestions...