Open SpadeLiu opened 2 years ago
Hi,
Should the label (Line 75) for stereo contrastive loss be a one-hot vector? It seems the label in the code is a all-zero vector.
On the other hand, when we generate random shift for the negative samples (Line 151~Line 164), why we split "n_neg" as "shift1" and "shift2"?
Hi,
Should the label (Line 75) for stereo contrastive loss be a one-hot vector? It seems the label in the code is a all-zero vector.
On the other hand, when we generate random shift for the negative samples (Line 151~Line 164), why we split "n_neg" as "shift1" and "shift2"?