@ShikunLi Hi, I find an error in the compute of unsupervised mask of mixed image, here we should let mask2Unsup_batch be the same mask matrix as maskUnsup_batch and mask2Unsup_mem be the same as maskUnsup_mem.
Because we passpairwise_comp_batch to function Supervised_ContrastiveLearning_loss and elements in pairwise_comp_batch is positive diagnally.
@ShikunLi Hi, I find an error in the compute of unsupervised mask of mixed image, here we should let
mask2Unsup_batch
be the same mask matrix asmaskUnsup_batch
andmask2Unsup_mem
be the same asmaskUnsup_mem
.Because we pass
pairwise_comp_batch
to functionSupervised_ContrastiveLearning_loss
and elements inpairwise_comp_batch
is positive diagnally.