search

yuruntian / L2-Net

Code and mode for CVPR 2017 paper "L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space"
111 stars 36 forks source link

questions about training process of batch normalize layer #5

Open appleleaves opened 6 years ago

appleleaves commented 6 years ago

there are some statements needed to make sure:

  1. while the weighting and bias are fixed at 1 and 0 respectfully,### the mean and var in it should be learned in the training process. Right?

2.the author state in the paper that the bn layer before DIF is not learned. Then it is the mean and var are calculated every time for different input?

yuruntian commented 6 years ago

@appleleaves for all the bn layers the affine parmameters are fixed at 1 and 0, but the mean and var are learned.