Reduce amount of memory required by mining strategies
joein opened this issue · 2 comments
joein commented
E.g. in semi-hard mining we use cubic matrix and it consumes lots of memory.
quaterion/quaterion/loss/triplet_loss.py
Line 157 in f2be2a4
Due to this usage of memory train_cifar100_with_xbm.py
crashes even on 3090Ti with "GPU out of memory" (after it exceeds start_iteration
and starts computing xbm loss)
monatis commented
This is a known issue marked as TODO. Currently it allows to use XBM with smaller batches. We postponed it to be handled later on --you can assign it to me if you aren't working on it already.