Same permutation for all audio samples?

[kmalhotra30]

Hello,

In the 3rd sampling strategy (sampling from same sequence) for audio subtask, I noticed that the permutation of negative samples is same for all audio sequences in the batch. This is not necessarily incorrect, but it can introduce some sort a bias based on locations of negative samples.

I think it would be better to have random permutations for all audio samples and the fix is easy :)

Reference :

Greedy_InfoMax/GreedyInfoMax/audio/models/loss_InfoNCE.py

Line 124 in 21b2aad

elif self.opt.sampling_method == 2:

[loeweX]

Hi,
Thanks for your interest in my repo.
How would you fix the sampling?

[kmalhotra30]

Hey , sorry for the late response! I have opened a pull request! Kindly take a look :)

Thanks
Karan