We see a reduction in number of parameters from 1.4*10⁸ to 4*10³ which is 5 orders of magnitude. So we should be fine collecting less than hundred images of dresses.
NanoNets : How to use Deep Learning when you have Limited Data
Sarthak Jain

How does the conclusion of ‘less than 100’ come up from the parameters? How did you come up with that number — less than 100?

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.