def downsample(layer_input, filters, f_size=4):
d = Conv2D(filters, kernel_size=f_size, strides=2,
padding='same')(layer_input)
d = InstanceNormalization(axis=-1)(d)
d = Activation('relu')(d)
return d
def downsample(layer_input, filters):
y = Conv2D(filters,
kernel_size=(3, 3),
strides=2,
padding='same',
kernel_initializer=self.weight_init)(layer_input)
y = InstanceNormalization(axis=-1)(y)
y = Activation('relu')(y)
return y
def residual(layer_input, filters):
shortcut = layer_input
y = ReflectionPadding2D(padding=(1, 1))(layer_input)
y = Conv2D(filters,
kernel_size=(3, 3),
strides=1,
padding='valid',
kernel_initializer=self.weight_init)(y)
y = InstanceNormalization(axis=-1)(y)
y = Activation('relu')(y)
y = ReflectionPadding2D(padding=(1, 1))(y)
y = Conv2D(filters,
kernel_size=(3, 3),
strides=1,
padding='valid',
kernel_initializer=self.weight_init)(y)
y = InstanceNormalization(axis=-1)(y)
return add([shortcut, y])
def conv4(layer_input, filters, stride=2, norm=True):
y = Conv2D(filters,
kernel_size=(4, 4),
strides=stride,
padding='same',
kernel_initializer=self.weight_init)(layer_input)
if norm:
y = InstanceNormalization(axis=-1)(y)
y = LeakyReLU(0.2)(y)
return y
def conv7s1(layer_input, filters, final):
y = ReflectionPadding2D(padding=(3, 3))(layer_input)
y = Conv2D(filters,
kernel_size=(7, 7),
strides=1,
padding='valid',
kernel_initializer=self.weight_init)(y)
if final:
y = Activation('tanh')(y)
else:
y = InstanceNormalization(axis=-1)(y)
y = Activation('relu')(y)
return y
def upsample(layer_input,
skip_input,
filters,
f_size=4,
dropout_rate=0):
u = UpSampling2D(size=2)(layer_input)
u = Conv2D(filters, kernel_size=f_size, strides=1,
padding='same')(u)
u = InstanceNormalization(axis=-1)(u)
u = Activation('relu')(u)
if dropout_rate:
u = Dropout(dropout_rate)(u)
u = Concatenate()([u, skip_input])
return u