Hacker News new | past | comments | ask | show | jobs | submit login

You could probably apply the same code. The dataset ("acquire 75,471 sketches of 12,500 objects") sounds adequate, and if not, can be boosted by first training a CNN to do photo->sketch (throwing away information is usually easier than imagining it) and using that to boost the dataset for sketch->photo.



Consider applying for YC's Spring batch! Applications are open till Feb 11.

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

Search: