Samuel

why do you multiply mul(1.0-1.0/s[1]).mul(n) ?

1

Hi, In your gradient update, you multiplied mul(1.0-1.0/s[1]).mul(n) to the gradient, which does not appear in your note.pdf. Could you explain why you multiplied these two terms? Thanks

update .bst file to correct a typesetting error in reference.

Hi May I know what the dataset did you use. Is it possible to release the dataset? Thanks

Hi, could you provide the link of warehouse dataset? Thanks

Is there pretrained models in pytorch to share?