Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on YOLO: Real-Time Object Detection. Parent comment
The idea is to add an extra 2 params to the output of each classifier cell. Then do L2 normalization on them ( https://github.com/indutny/resistenz/blob/master/python/mode... ) and treat them as a cosine/sine pair.
The loss in this case would be the Euclidean distance between the actual and predicted pairs, which is equal to "2 * (1 - cos(x-y))".
There are no comments on this comment yet.
The idea is to add an extra 2 params to the output of each classifier cell. Then do L2 normalization on them ( https://github.com/indutny/resistenz/blob/master/python/mode... ) and treat them as a cosine/sine pair.
The loss in this case would be the Euclidean distance between the actual and predicted pairs, which is equal to "2 * (1 - cos(x-y))".