Purpose of Memory Bank
HenryPengZou opened this issue · 2 comments
HenryPengZou commented
Hi, thanks for your great work!
I have a question regarding the usage of the memory bank when mining nearest neighbors in the following lines:
Unsupervised-Classification/tutorial_nn.py
Lines 54 to 65 in a1fecf2
Can't we directly mine nearest neighbors from base_dataset
and val_dataset
? Why do we bother to use the memory bank?
Thanks a lot for your help in advance.
wvangansbeke commented
Hi @HenryPengZou,
The memory bank is used to store the features for all images and subsequently mine the nearest neighbors for each image (see MemoryBank.update
method. The base_dataset
is used to adopt a different set of augmentations (i.e. validation set augmentations).
HenryPengZou commented
I see, thank you~