BatchNorm momentum

[Anzoteh96]

Hello,

Not too sure if it's an appropriate to raise this, but I felt it strange that the momentum of batch normalization is set to 0 here:

crowdcount-mcnn/src/network.py

Line 11 in e04c67f

self.bn = nn.BatchNorm2d(out_channels, eps=0.001, momentum=0, affine=True) if bn else None

According to the documentation it seems that we use the average value of the first batch ever seen.

I wonder if this is intended since many guides suggest 0.1, 0.01, etc (but not 0).