Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
deepthrowaway's comments
login
deepthrowaway
on Nov 1, 2017
|
parent
|
context
[–]
| on:
Fooling Neural Networks in the Physical World with...
The inception network tested is not trained for multilabel classification problem, I believe it would be harder to function against a multi label network such as inception trained on Open Images dataset.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: