def forward(self, input):
BaumOut, mask = self.Baum(input)
abc = self.features(self.input_norm(input))
a = (abc[:, 0, :, :].contiguous())
b = (abc[:, 1, :, :].contiguous())
c = (abc[:, 2, :, :].contiguous())
return abc2A(a, b, c) + BaumOut, 1.0
def forward(self,x):
if x.is_cuda:
self.gk = self.gk.cuda()
else:
self.gk = self.gk.cpu()
gx = self.gx(F.pad(x, (1, 1, 0, 0), 'replicate'))
gy = self.gy(F.pad(x, (0, 0, 1, 1), 'replicate'))
a1 = (gx * gx * self.gk.unsqueeze(0).unsqueeze(0).expand_as(gx)).view(x.size(0),-1).mean(dim=1)
b1 = (gx * gy * self.gk.unsqueeze(0).unsqueeze(0).expand_as(gx)).view(x.size(0),-1).mean(dim=1)
c1 = (gy * gy * self.gk.unsqueeze(0).unsqueeze(0).expand_as(gx)).view(x.size(0),-1).mean(dim=1)
a, b, c, l1, l2 = self.invSqrt(a1,b1,c1)
rat1 = l1/l2
mask = (torch.abs(rat1) <= 6.).float().view(-1);
return abc2A(a,b,c), mask
def forward(self, input):
abc = self.features(self.input_norm(input))
return abc2A(abc[:,0,:,:] + 1. ,abc[:,1,:,:] , abc[:,2,:,:] + 1.):
def forward(self, input):
abc = self.features(self.input_norm(input))
a = (abc[:, 0, :, :].contiguous() + 1.0)
b = (abc[:, 1, :, :].contiguous() + 0.0)
c = (abc[:, 2, :, :].contiguous() + 1.0)
return abc2A(a, b, c), 1.0
def forward(self, input):
abc = self.features(self.input_norm(input))
return abc2A(abc[:, 0, :, :].contiguous() + 1.,
abc[:, 1, :, :].contiguous(),
abc[:, 2, :, :].contiguous() + 1.)
