[ ] Segments with high coverage ratio should be more likely to be selected i.e. sampling based on cov_ratio_per_segment.
[x] define appropriate values for RATIO_INTERVALS
[x] main bug is here. index i is iterating over videos while score.shape[0] corresponds to the number of segments for all the videos. My fault :disappointed:
Note: if t_size is closer to l_size is possible that not enough segments are generated to satisfy a uniform distribution on RATIO_INTERVALS. We should decide how to overcome it.
main bug was updated + notebook with example of how to use compute_priors. It would be great that you check if something looks weird there anyway :wink:
I wrote this function replicating the idea of the cvpr-paper. It would be great to refine it in the following aspects:
t_size
.cov_ratio_per_segment
.RATIO_INTERVALS
i
is iterating over videos whilescore.shape[0]
corresponds to the number of segments for all the videos. My fault :disappointed:Note: if
t_size
is closer tol_size
is possible that not enough segments are generated to satisfy a uniform distribution onRATIO_INTERVALS
. We should decide how to overcome it.