Closed vanity1129 closed 11 months ago
Hi, Thanks for pointing out this issue! It is indeed a typo. You can safely delete it. I believe It is originally designed to mask off uneffective pairs, i.e., prototypes and themselves.
Okay, Thx for your reply~
Hi, @LzVv123456
May I ask what is the practical meaning of the code in lines 189-191 in the losses.py file because they look syntax-wrong and do not execute anything.
# mask off pairs among prototypes p_mask[sample_num+1: sample_num+1:] = 0 n_mask[sample_num+1: sample_num+1:] = 0