@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_batchbe the same mask matrix asmaskUnsup_batchandmask2Unsup_membe the same asmaskUnsup_mem.Because we pass
pairwise_comp_batchto functionSupervised_ContrastiveLearning_lossand elements inpairwise_comp_batchis positive diagnally.