Aleksei Shabanov

Any news?

IMHO, this loss is not additive by design (like f1 score)

So, features should be collected over the virtual batches and then loss should be applied

@deepslug okay, I got your point

Changes from this PR have been moved to other PRs: * https://github.com/OML-Team/open-metric-learning/pull/568 * https://github.com/OML-Team/open-metric-learning/pull/567 * https://github.com/OML-Team/open-metric-learning/pull/566

Hi, @snow-wind-001 It's a known problem. The current implementation requires storing 450k x 450k floats in your memory. Right now I'm working on the solution to make it memory optimized....

@Rei-Moriaty Yes, sure. If you run one of the examples (for instance, training model on INSHOP dataset) you will see a lot of graphs with metrics by different categories on...

@isehmi Hi, it would be fine, because it's still an active problem As for imports, ideally, all of the have to be accessible in collab env 1) Do other imports...

@isehmi Hm, after what you said, I created an empty docker container with python and successfully installed the library from PIP. Which OS do you have?

@isehmi Got it. I think this is a problem. We have not tested the installation of our library for windows. Only unix-like systems. As for lightning and colab, yes, it's...