Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
tripzilch
on June 3, 2016
|
parent
|
context
|
favorite
| on:
Blade Runner re-encoded using neural networks
This network was trained on a single NVidia 960 GPU for two weeks, I wonder how much better it could have been with more computing power thrown at it?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
