This version jump was quite time and resourse consuming. There was 8 iterations before I and my gf agreed that this is better than the previous (in average, though, not overwhelmingly).
Technically, there were just two more vectors added. "Just two!? And that took you a couple months?" - one may ask. Well, that it because the idea of this embedding is to be more like a scalpel, not a hammer. The hardest part was to tweak weights to achieve three things: be better than the previous, have the least impact on the composition and be useful for each and every occasion.
Keep in mind, that V2 can notisably change composition. The third comparison was chosen specifically to show this.
This version jump was quite time and resourse consuming. There was 8 iterations before I and my gf agreed that this is better than the previous (in average, though, not overwhelmingly).
Technically, there were just two more vectors added. "Just two!? And that took you a couple months?" - one may ask. Well, that it because the idea of this embedding is to be more like a scalpel, not a hammer. The hardest part was to tweak weights to achieve three things: be better than the previous, have the least impact on the composition and be useful for each and every occasion.
Keep in mind, that V2 can notisably change composition. The third comparison was chosen specifically to show this.