Very interesting article! It answered some questions I've had for a long time.
I'm curious about how this works in practice. Is it always good enough to take the outputs of the next-to-last layer as features? When doing quick iterations, I assume the images in the data set have been run through the big net as a preparation step? And the inputs to the net you're training is the features? Does the new net always only need 1 layer?
What are some examples of where this worked well (except for the flowers mentioned in the article)?
I'm curious about how this works in practice. Is it always good enough to take the outputs of the next-to-last layer as features? When doing quick iterations, I assume the images in the data set have been run through the big net as a preparation step? And the inputs to the net you're training is the features? Does the new net always only need 1 layer?
What are some examples of where this worked well (except for the flowers mentioned in the article)?