def __init__(self, channels_img, features_d):
super(Discriminator, self).__init__()
# Input : N x C x 256 x 256
self.disc = nn.Sequential(
nn.Conv2D( # 128 x 128
channels_img,
features_d,
kernel_size=4,
stride=2,
padding=1,
weight_attr=paddle.ParamAttr(initializer=conv_initializer())),
nn.LeakyReLU(0.2),
self._block(features_d, features_d * 2, 4, 2, 1), # 64 x 64
self._block(features_d * 2, features_d * 4, 4, 2, 1), # 32 x 32
self._block(features_d * 4, features_d * 8, 4, 2, 1), # 16 x 16
self._block(features_d * 8, features_d * 16, 4, 2, 1), # 8 x 8
self._block(features_d * 16, features_d * 32, 4, 2, 1), # 4 x 4
nn.Conv2D(
features_d * 32,
1,
kernel_size=4,
stride=2,
padding=0, # 1 x 1
weight_attr=paddle.ParamAttr(initializer=conv_initializer())),
nn.Sigmoid(),
)
def __init__(self, z_dim, channels_img, features_g):
super(Generator, self).__init__()
self.gen = nn.Sequential(
# Input: N x z_dim x 1 x 1
self._block(z_dim, features_g * 64, 4, 1, 0), # N x f_g x 4 x 4
self._block(features_g * 64, features_g * 32, 4, 2,
1), # N x f_g x 8 x 8
self._block(features_g * 32, features_g * 16, 4, 2,
1), # N x f_g x 16 x 16
self._block(features_g * 16, features_g * 8, 4, 2,
1), # N x f_g x 32 x 32
self._block(features_g * 8, features_g * 4, 4, 2,
1), # N x f_g x 64 x 64
self._block(features_g * 4, features_g * 2, 4, 2,
1), # N x f_g x 128 x 128
nn.Conv2DTranspose(
features_g * 2,
channels_img,
kernel_size=4,
stride=2,
padding=1,
bias_attr=False,
weight_attr=paddle.ParamAttr(initializer=conv_initializer())),
nn.Tanh() # [-1, 1]
)
def _block(self, in_channels, out_channels, kernel_size, stride, padding):
return nn.Sequential(
nn.Conv2D(
in_channels, out_channels, kernel_size, stride, padding, bias_attr=False,
weight_attr=paddle.ParamAttr(initializer=conv_initializer() )
),
nn.LeakyReLU(0.2),
)
def _block(self, in_channels, out_channels, kernel_size, stride, padding):
return nn.Sequential(
nn.Conv2DTranspose(
in_channels, out_channels, kernel_size, stride, padding, bias_attr=False,
weight_attr=paddle.ParamAttr(initializer=conv_initializer() )
),
nn.BatchNorm2D(
out_channels,
weight_attr=paddle.ParamAttr(initializer=bn_initializer() ) ,
momentum=0.8
),
nn.ReLU(),
)