Ensure positive index is not chosen in negatives

[Senthil Purushwalkam]

Shouldn't you ensure idx != y here?
This probably is not a big deal for ImageNet-scale datasets, but might cause issues in smaller datasets.

lemniscate.pytorch/lib/NCEAverage.py

Line 88 in 34c7ce3

 idx = self.multinomial.draw(batchSize * (self.K+1)).view(batchSize, -1) 

[zhirongw]

@senthilps8 , I guess you are absolutely correct. The code here is not exactly right.
In smaller dataset, sampling is actually not needed. You can switch to the full softmax loss as in Cifar10.

[Yonglong Tian]

@senthilps8 , according to my observation, this does not affect the final performance.

[Senthil Purushwalkam]

@HobbitLong Thanks for confirming.