Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
PartiallyTyped
on March 8, 2021
|
parent
|
context
|
favorite
| on:
Finding Mona Lisa in the Game of Life
What you are suggesting is the idea behind StyleTransfer. Given two images, A, B, and a neural network F, you repeatedly modify B using ∂ L(F(A),F(B))/∂B, where L is the loss function, A contains the style and B is the input image.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: