def __init__(self, ngpu, ndf, nc, k):
super(Discriminator, self).__init__()
self.ngpu = ngpu
layers = []
layers.append(nn.Conv2d(nc, ndf, kernel_size, stride=stride, padding=padding, bias=False) )
layers.append(nn.LeakyReLU(0.2, inplace=True))
# state size. (ndf) x 64 x 64
#--------------------------------------------
for i in range(k):
layers.append(ll.DisLayerSN_d(ndf, i))
#--------------------------------------------
d_out = 2**k
layers.append(sa.Self_Attn(ndf*d_out, "relu"))
layers.append(sa.Self_Attn(ndf*d_out, "relu"))
layers.append(nn.Conv2d(ndf * d_out, 1, kernel_size, stride=1, padding=0, bias=False))
layers.append(nn.Sigmoid())
# state size. 1
self.main = nn.ModuleList(layers)
def __init__(self, ngpu, nz, ngf, nc, k):
super(Generator, self).__init__()
self.ngpu = ngpu
layers = []
d_in = 2**k
layers.append( nn.ConvTranspose2d( nz, ngf * d_in, kernel_size, 1, 0, bias=False) )
layers.append( nn.BatchNorm2d(ngf * d_in) )
layers.append( nn.ReLU(True) )
# state size. (ngf*16) x 4 x 4
#------------------------------------------
for i in range(k):
n = k-i
layers.append( ll.GenLayerSN(ngf, n) )
#------------------------------------------
layers.append(sa.Self_Attn(ngf,"relu"))
layers.append(sa.Self_Attn(ngf,"relu"))
layers.append(nn.ConvTranspose2d( ngf, nc, kernel_size, stride, padding, bias=False) )
layers.append(nn.Tanh() )
# state size. (nc) x 128 x 128
self.main = nn.ModuleList(layers)
def __init__(self, ngpu, nz, ngf, nc, k):
super(Generator, self).__init__()
self.ngpu = ngpu
layers = []
d_in = stride**2
layers.append(
nn.ConvTranspose2d(nz,
ngf * d_in,
kernel_size,
stride,
padding,
bias=False))
layers.append(nn.BatchNorm2d(ngf * d_in))
layers.append(nn.ReLU(True))
#------------------------------------------
layers.append(GenLayerSN(ngf, 2))
layers.append(GenLayerSN(ngf, 1))
#------------------------------------------
layers.append(sa.Self_Attn(ngf, "relu"))
layers.append(
nn.ConvTranspose2d(ngf,
nc,
kernel_size,
stride,
padding,
bias=False))
layers.append(nn.Tanh())
self.main = nn.ModuleList(layers)
def __init__(self, ngpu, ndf, nc, k):
super(Discriminator, self).__init__()
self.ngpu = ngpu
layers = []
layers.append(nn.Conv2d(nc, ndf, kernel_size, stride=stride, padding=padding, bias=False) )
layers.append(nn.LeakyReLU(0.2, inplace=True))
# state size. (ndf) x 64 x 64
k=4
# -------------------------------------------
# per immagini 64 x 64 ci volgliono 3 strati
# e k = 3
#
# per immagini 128 x 128 ci vogliono 4 strati
# e k = 4
#--------------------------------------------
layers.append(DisLayerSN_d(ndf, 0))
layers.append(DisLayerSN_d(ndf, 1))
layers.append(sa.Self_Attn(ndf*(2**2), "relu"))
layers.append(DisLayerSN_d(ndf, 2))
layers.append(DisLayerSN_d(ndf, 3))
#--------------------------------------------
d_out = 2**k
layers.append(sa.Self_Attn(ndf*d_out, "relu"))
layers.append(nn.Conv2d(ndf * d_out, 1, kernel_size, stride=1, padding=0, bias=False))
layers.append(nn.Sigmoid())
# state size. 1
self.main = nn.ModuleList(layers)
def __init__(self, ngpu, nz, ngf, nc, k):
super(Generator, self).__init__()
self.ngpu = ngpu
layers = []
k=4
d_in = 2**k
layers.append( nn.ConvTranspose2d( nz, ngf * d_in, kernel_size, 1, 0, bias=False) )
layers.append( nn.BatchNorm2d(ngf * d_in) )
layers.append( nn.ReLU(True) )
# state size. (ngf*16) x 4 x 4
# -------------------------------------------
# per immagini 64 x 64 ci volgliono 3 strati
# e k = 3
#
# per immagini 128 x 128 ci vogliono 4 strati
# e k = 4
#--------------------------------------------
#------------------------------------------
layers.append( GenLayerSN(ngf, 4) )
layers.append( GenLayerSN(ngf, 3) )
layers.append( GenLayerSN(ngf, 2) )
layers.append(sa.Self_Attn(ngf*(2**1),"relu"))
layers.append( GenLayerSN(ngf, 1) )
#------------------------------------------
layers.append(sa.Self_Attn(ngf,"relu"))
layers.append(nn.ConvTranspose2d( ngf, nc, kernel_size, stride, padding, bias=False) )
layers.append(nn.Tanh() )
# state size. (nc) x 128 x 128
self.main = nn.ModuleList(layers)