[ImageNet]
• Over 15M labeled high resolution images.
• Roughly 22k categories.
• Annual competition of image classification at large scale.
• 1.2M training images, 50k validation images, and 150k testing images.
• 1k categories.
• Resolution of each image varies.
• Classification: make 5 guesses about the image label (top-5 error).
• Deeper, bigger than LeNet.
• Featured conv layer stacked on top of each other (previously it was common to only have a single conv layer always immediately followed by a pool layer).
• First use of ReLU.
• Heavy data augmentation.
• Improvement on AlexNet by tweaking the architecture hyperparamet
• Over 15M labeled high resolution images.
• Roughly 22k categories.
• Collected from web and labeled by Amazon Mechanical Turk.
• Annual competition of image classification at large scale.
• 1.2M training images, 50k validation images, and 150k testing images.
• 1k categories.
• Resolution of each image varies.
• Classification: make 5 guesses about the image label (top-5 error).
[Architectures] See Tab. 1.
AlexNet• Deeper, bigger than LeNet.
• Featured conv layer stacked on top of each other (previously it was common to only have a single conv layer always immediately followed by a pool layer).
• First use of ReLU.
• Heavy data augmentation.
• Dropout.
• Improvement on AlexNet by tweaking the architecture hyperparamet