calculating S and Z values in the Uniform Quantization equantion

[lovodkin93]

Hello,
I am trying to implement your quantization method in my system (Q(r)=Int(r/S) + Z), and I keep having very weird behavior.
going through your code - I saw that for weight quantization, Z=0 and for S:

n = 2 ** (num_bits - 1) - 1
if per_channel:
    scale, _ = torch.max(torch.stack([saturation_min.abs(), saturation_max.abs()], dim=1), dim=1)
    scale = torch.clamp(scale, min=1e-8) / n
else:
    scale = max(saturation_min.abs(), saturation_max.abs())
    scale = torch.clamp(scale, min=1e-8) / n

what I didn't manage to figure out is, how do you calculate saturation_min and saturation_max.
It looks like they are the max and min of the weights, but the weights are learnt - so are they the max and min before the gradient descent or after the update of the weights?