5,337
edits
Line 300: | Line 300: | ||
===Start of Lecture (Oct 6)=== | ===Start of Lecture (Oct 6)=== | ||
;Non-max Supression | |||
The NMS heuristic here is used to reduce the number of bounding boxes per object to 1. | |||
Initially, you have a set of overlapping bounding boxes <math>B</math>. | |||
Create a final set <math>D</math>. | |||
* While B is not empty | |||
** Remove the highest confidence box <math>b_i</math> from <math>B</math>. Add it to <math>D</math> | |||
** For every other box <math>b_j</math>, | |||
*** If <math>IOU(b_i, b_j) > \lambda</math> (i.e. they bound the same object), discard <math>b_j</math> | |||
;Hard mining | ;Hard mining | ||
During training, classify on all images. | During training, classify on all images. |