I'd expect that, but I think that it would be interesting to see how many negative images you would need to put into the training data to …
-
-
-
…achieve what levels of recognition also for negatives. Maybe only 10% of the images would need to also be added as negative to get 90%.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.