Why do you use Euclidean distance as the metric of fts' similarity?

[zhoumumu]

Hi! Thank you very much for your work! The preprocessing trimming code runs smoothly and it has been very helpful.

I'm curious as to why you chose to use Euclidean distance instead of cosine distance. Since the former has not been normalized to the range (0, 1), and thus difficult to select an appropriate threshold.

[zhoumumu]

In addition, what does this line used for?

Panda-70M/splitting/event_stitching.py

Line 107 in bbae2b1

if len(events[-1]) == 0: