search

zrl4836 / ACFNet

ACFNet: Attentional Class Feature Network for Semantic Segmentation.(ICCV2019)
79 stars 12 forks source link

normalize #5

Open Bio-shine opened 3 years ago

Bio-shine commented 3 years ago

# multiply & normalize ->(B, N, C') energy = torch.bmm(proj_query, proj_key) energy_new = torch.max(energy, -1, keepdim=True)[0].expand_as(energy) - energy

I think the normalization implemented in acfnet.py is different from the equation (2) in the original paper. And I wonder why you implement this way.

zzw1123 commented 3 years ago

I have the same question. Have you figured it out?