Self-supervision but actually using labels #4

Hi,
the work should rely on self supervision, where no labels are used for training, as stated in the README:

We DO NOT use the labels of the videos in any way during training, and only use them for evaluation.

However, labels are actually used in chosing the negative pairs for the contrastive loss. This is either a bug or not fair. However I reckon choosing negative pairs randomly should not make much difference, given the high number of classes (approx p=1/50 of taking a wrong pair).