This isn't exactly Deep Dream's equivalent for video. It takes frames individual... | Hacker News

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

JacobEdelman on July 11, 2015 | parent | context | favorite | on: DeepDreamVideo

This isn't exactly Deep Dream's equivalent for video. It takes frames individually (smushing them together), rather than having a unified neural network that takes the entire video at once.

tacos on July 11, 2015 [–]

It's also using low-quality jpegs as source and destination output so a good chunk of what you're seeing is the robot dreaming about jpeg artifacts.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact