search

qdrant / quaterion

Blazing fast framework for fine-tuning similarity learning models
https://quaterion.qdrant.tech/
Apache License 2.0
640 stars 45 forks source link

Reduce amount of memory required by mining strategies #182

Closed joein closed 1 year ago

joein commented 2 years ago

E.g. in semi-hard mining we use cubic matrix and it consumes lots of memory.

https://github.com/qdrant/quaterion/blob/f2be2a4a7ba00f4484090222838898ce73e7d682/quaterion/loss/triplet_loss.py#L157

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 2 years ago

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.

monatis commented 1 year ago

Completed in #186