audio-text_retrieval

audio-text_retrieval copied to clipboard

How to to obtain the downstream retrieval performace?

1

I wish to do a reproducibility study of this work.

anshumansinha16

Need help to train on another GPU

5

Hello, we are trying to set up and train the models on Mac M2 10-core GPU with 8GB RAM with MPS framework and also a GTX 1650 Ti with 4GB...

devcuriyash

Understanding the NT-Xent loss function

1

Could you explain the significance of mask in the NT-Xent loss function? ``` mask = labels.expand(n, n).eq(labels.expand(n, n).t()).to(a2t.device) mask_diag = mask.diag() mask_diag = torch.diag_embed(mask_diag) mask = mask ^ mask_diag a2t_loss...

Vedanshi-Shah