Learned representations after pretext task

[emessori]

Hi @wvangansbeke.
First of all, thank you for your work!
I managed to run your program with a custom dataset: however, despite obtaining nearest neighbors that at a naked eye seem 'good', the clustering step is not yielding satisfying results at the moment. I am currently running this step with different hyperparameters that may be more appropriate for my dataset, but I was wondering whether there was a way to retrieve the representation learned through the pretext task; I supposed that I should focus on output = model(input__).view(b, 2, -1) here but I am not sure about it. Could you please provide some clues or insights about it?

P.s. I checked issue #53 but it was not helpful for my task.

[akshay-iyer]

You could save the features in the mine_nearest_neighbors function. Those are your representations

[emessori]

Thank you so much for answering: in fact, that is what I decided to do, but it's nice to have confirmation that's right.
Do the learned representations refer to the "original" images or to their augmented versions?

Thank you again!