yhhhli / APoT_Quantization

PyTorch implementation for the APoT quantization (ICLR 2020)
258 stars 51 forks source link

difference between paper and code in quan_layer #24

Open EwainPeng opened 1 year ago

EwainPeng commented 1 year ago

Hi~ I have a liitle puzzled about a difference between paper and code in quan_layer.py. In paper, when B = 4 P0∈{0,2^0,2^-2,2^-4} (show in example in 2.2) But in code quan_layer.py line 23: base_b.append(2 * (-2 i - 2)), when i range(3) we have P0∈{0,2^-2,2^-4,2^-6} I am a little puzzled about it, thanks a lot!

Minato-Zackie commented 1 year ago

I have the same question as EwainPeng. Why the sum of n PoT terms of each level is different from the paper? Looking forward to your reply!

lllkjh commented 1 month ago

@Minato-Zackie @EwainPeng Hello guys, did you figure this question out? thx