You would lose information from the texture of the image that way. It's already ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		sp332 on Dec 24, 2015 \| parent \| context \| favorite \| on: How to trick a neural network into thinking a pand... You would lose information from the texture of the image that way. It's already downscaled to 224 pixels square, so you'd really be restricting the amount of data available to the function.

awqrre on Dec 26, 2015 [–]

of course you would loose some information but it is probably not enough to mis-identify most objects..

Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact