image-similarity-deep-ranking icon indicating copy to clipboard operation
image-similarity-deep-ranking copied to clipboard

Published 20 hours ago • verified publisher icon akarshzingade

About subsample and produce triplet.txt

Open longzeyilang opened this issue 6 years ago • 3 comments

Hi, According to the original，I have two question below:

  1. the original use muti-scale model, you demo can not use, why?
  2. the original use pairwise relevance scores to choose the better positive and negative image sample, in this demo, do not use the mentioned rules. why? Thanks a lot!

longzeyilang avatar Jul 01 '18 06:07 longzeyilang

Hey Longzeyilang!

  1. Do you mean the parallel smaller network with VGG? If yes, I do have implemented it :)
  2. The pairwise relevance score is hand crafted. Unfortunately, they haven't open-sourced that information so couldn't use it.

akarshzingade avatar Jul 03 '18 13:07 akarshzingade

Thank you! I have another problem, the returned value batch_y of train_generator function not use in the train. if batch_y is all the same, it does not matter!

longzeyilang avatar Jul 04 '18 07:07 longzeyilang

Yes, that is correct! I was supposed to change this. But, somehow forgot about it! Thank you for pointing that out :)

akarshzingade avatar Jul 06 '18 05:07 akarshzingade