Open Bio-shine opened 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
# 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.
I have the same question. Have you figured it out?
# 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.