def __call__(self, input):
with tf.variable_scope(self.name, reuse=self.reuse):
input = ly.fc(input, 7 * 7 * 128, name='fc_0')
input = ly.bn_layer(input, name='bn_0')
input = tf.nn.leaky_relu(input)
input = tf.reshape(input, (-1, 7, 7, 128))
input = ly.deconv2d(input,
output_channel=64,
output_size=14,
strides=2,
name='deconv_0')
input = ly.bn_layer(input, name='bn_1')
input = tf.nn.leaky_relu(input)
input = ly.deconv2d(input,
output_channel=1,
output_size=28,
strides=2,
name='deconv_1')
input = ly.bn_layer(input, name='bn_2')
input = tf.nn.sigmoid(input)
return input ## (-1,28,28,1)
def __call__(self, input):
### input_shape [-1,128,128,3]
input_shape = input.get_shape().as_list()
with tf.variable_scope(self.name, reuse=self.reuse):
input = ly.conv2d(input,
64,
kernel_size=4,
strides=2,
name='d_conv_0') # [-1,64,64,64]
input = ly.bn_layer(input, name='d_bn_0')
input = tf.nn.relu(input)
input = ly.conv2d(input,
128,
kernel_size=4,
strides=2,
name='d_conv_1') # [-1,32,32,128]
input = ly.bn_layer(input, name='d_bn_1')
input = tf.nn.relu(input)
input = ly.conv2d(input,
256,
kernel_size=4,
strides=2,
name='d_conv_2') # [-1,16,16,256]
input = ly.bn_layer(input, name='d_bn_2')
input = tf.nn.relu(input)
input = ly.conv2d(input,
512,
kernel_size=4,
strides=2,
name='d_conv_3') # [-1,8,8,512]
input = ly.bn_layer(input, name='d_bn_3')
input = tf.nn.relu(input)
input = ly.conv2d(input,
1,
kernel_size=4,
strides=1,
name='d_conv_4',
bias=True)
input = tf.nn.sigmoid(input)
self.reuse = True
return input
def __call__(self, input):
with tf.variable_scope(self.name, reuse=self.reuse):
input = ly.conv2d(input, 64, strides=2,
name='conv2d_0') # 14 14 64
input = ly.bn_layer(input, name='bn_0')
input = tf.nn.relu(input)
input = ly.conv2d(input, 128, strides=2,
name='conv2d_1') # 7 7 128
input = ly.bn_layer(input, name='bn_1')
input = tf.nn.relu(input)
input = ly.fc(input, 1024, name='fc_0')
input = tf.nn.relu(input)
input = ly.fc(input, 10, name='fc_1')
return input
def __call__(self, input):
with tf.variable_scope(self.name, reuse=self.reuse):
input = ly.conv2d(input, 64, strides=2, name='d_conv2d_0')
input = tf.nn.leaky_relu(input)
input = ly.conv2d(input, 128, strides=2, name='d_conv2d_1')
input = ly.bn_layer(input, name='d_bn_1')
input = tf.nn.leaky_relu(input)
input = ly.conv2d(input, 256, strides=2, name='d_conv2d_2')
input = ly.bn_layer(input, name='d_bn_2')
input = tf.nn.leaky_relu(input)
input = ly.conv2d(input, 512, strides=2, name='d_conv2d_3')
input = ly.bn_layer(input, name='d_bn_3')
input = tf.nn.leaky_relu(input)
input = ly.fc(input, 1, bias=True, name='d_fc_0')
return tf.nn.sigmoid(input)
def __call__(self, input):
height = input.get_shape().as_list()[1]
with tf.variable_scope(self.name, reuse=self.reuse):
input = ly.conv2d(input, 64, name='g_conv2d_0')
input = ly.bn_layer(input, name='g_bn_0')
input = tf.nn.relu(input)
### resnet
for i in range(16):
cell = ly.conv2d(input, 64, name='g_res_conv2d_%s' % i)
cell = ly.bn_layer(cell, name='g_res_bn_%s' % i)
cell = input + cell
input = cell
### deconv2d
input = ly.conv2d(input, 256, name='g_conv2d_1')
input = ly.deconv2d(input, 128, height * 2, strides=2, name='g_deconv2d_0')
input = tf.nn.relu(input)
input = ly.conv2d(input, 128, name='g_conv2d_2')
input = ly.deconv2d(input, 64, height * 4, strides=2, name='g_deconv2d_1')
input = tf.nn.relu(input)
# ### Upsampling
# input = ly.conv2d(input,256,name = 'g_conv2d_1')
#
# input = ly.Upsampling(input,height * 2)
# input = ly.conv2d(input, 128,name = 'g_conv2d_2')
# input = ly.bn_layer(input,name = 'g_bn_2')
#
# input = ly.Upsampling(input,height * 4)
# input = ly.conv2d(input, 64,name = 'g_conv2d_3')
# input = ly.bn_layer(input,name = 'g_bn_3')
input = ly.conv2d(input, 3, name='g_conv2d_last')
input = tf.nn.tanh(input)
return input
def __call__(self, input):
with tf.variable_scope(self.name, reuse=self.reuse):
input = ly.conv2d(input, 64, strides=2,
name='conv_0') ## (-1,14,14,64)
input = ly.bn_layer(input, name='bn_0')
input = tf.nn.leaky_relu(input)
input = ly.conv2d(input, 128, strides=2,
name='conv_1') ## (-1,7,7,128)
input = ly.bn_layer(input, name='bn_1')
input = tf.nn.leaky_relu(input)
output_d = ly.fc(input, 1, name='fc_0')
output_d = ly.bn_layer(input, name='bn_2')
# output_label = ly.fc(input, 128,name = 'label_fc_0')
# input = ly.bn_layer(input, name='bn_3')
# input = tf.nn.leaky_relu(input)
#
# output_label = ly.fc(input, 1,name = 'label_fc_1')
# input = ly.bn_layer(input, name='bn_4')
# input = tf.nn.sigmoid(input)
return output_d
def __call__(self, input):
### simple
with tf.variable_scope(self.name, reuse=self.reuse):
input = ly.conv2d(input, 64, name='d_conv2d_0')
input = ly.conv2d(input, 64, strides=2, name='d_conv2d_1')
input = ly.bn_layer(input, name='d_bn_1', gamma_initializer=tf.random_normal_initializer(1., 0.02))
input = tf.nn.leaky_relu(input)
input = ly.conv2d(input, 128, strides=1, name='d_conv2d_2')
input = ly.bn_layer(input, name='d_bn_2', gamma_initializer=tf.random_normal_initializer(1., 0.02))
input = tf.nn.leaky_relu(input)
input = ly.conv2d(input, 128, strides=2, name='d_conv2d_3')
input = ly.bn_layer(input, name='d_bn_3', gamma_initializer=tf.random_normal_initializer(1., 0.02))
input = tf.nn.leaky_relu(input)
input = ly.conv2d(input, 256, strides=1, name='d_conv2d_4')
input = ly.bn_layer(input, name='d_bn_4', gamma_initializer=tf.random_normal_initializer(1., 0.02))
input = tf.nn.leaky_relu(input)
input = ly.conv2d(input, 256, strides=2, name='d_conv2d_5')
input = ly.bn_layer(input, name='d_bn_5', gamma_initializer=tf.random_normal_initializer(1., 0.02))
input = tf.nn.leaky_relu(input)
input = ly.conv2d(input, 512, strides=1, name='d_conv2d_6')
input = ly.bn_layer(input, name='d_bn_6', gamma_initializer=tf.random_normal_initializer(1., 0.02))
input = tf.nn.leaky_relu(input)
input = ly.conv2d(input, 512, strides=2, name='d_conv2d_7')
input = ly.bn_layer(input, name='d_bn_7', gamma_initializer=tf.random_normal_initializer(1., 0.02))
input = tf.nn.leaky_relu(input)
print(input.shape)
input = ly.fc(input, 1024, name='d_fc_0')
input = tf.nn.leaky_relu(input)
input = ly.fc(input, 1, name='d_fc_1')
input = tf.nn.sigmoid(input)
return input
def __call__(self, input): # 256 * 256 * 3
with tf.variable_scope(self.name, reuse=self.reuse):
e0 = ly.conv2d(input, 64, strides=2,
name='g_conv2d_0') # 128 * 128 * 64
e0 = ly.bn_layer(e0, name='g_bn_0')
e0 = tf.nn.leaky_relu(e0)
e1 = ly.conv2d(e0, 128, strides=2,
name='g_conv2d_1') # 64 * 64 * 128
e1 = ly.bn_layer(e1, name='g_bn_1')
e1 = tf.nn.leaky_relu(e1)
e2 = ly.conv2d(e1, 256, strides=2,
name='g_conv2d_2') # 32 * 32 * 256
e2 = ly.bn_layer(e2, name='g_bn_2')
e2 = tf.nn.leaky_relu(e2)
e3 = ly.conv2d(e2, 512, strides=2,
name='g_conv2d_3') # 16 * 16 * 512
e3 = ly.bn_layer(e3, name='g_bn_3')
e3 = tf.nn.leaky_relu(e3)
e4 = ly.conv2d(e3, 512, strides=2,
name='g_conv2d_4') # 8 * 8 * 512
e4 = ly.bn_layer(e4, name='g_bn_4')
e4 = tf.nn.leaky_relu(e4)
e5 = ly.conv2d(e4, 512, strides=2,
name='g_conv2d_5') # 4 * 4 * 512
e5 = ly.bn_layer(e5, name='g_bn_5')
e5 = tf.nn.leaky_relu(e5)
e6 = ly.conv2d(e5, 512, strides=2,
name='g_conv2d_6') # 2 * 2 * 512
e6 = ly.bn_layer(e6, name='g_bn_6')
e6 = tf.nn.leaky_relu(e6)
e7 = ly.conv2d(e6, 512, strides=2,
name='g_conv2d_7') # 1 * 1 * 512
e7 = ly.bn_layer(e7, name='g_bn_7')
e7 = tf.nn.leaky_relu(e7)
d1 = ly.deconv2d(e7, 512, 2, strides=2,
name='g_deconv2d_1') # 2 * 2 * 512
d1 = ly.bn_layer(d1, name='g_bn_8')
d1 = tf.nn.dropout(tf.nn.leaky_relu(d1), 0.5)
d1 = tf.concat([d1, e6], 3)
d2 = ly.deconv2d(d1, 512, 4, strides=2,
name='g_deconv2d_2') # 4 * 4 * 512
d2 = ly.bn_layer(d2, name='g_bn_9')
d2 = tf.nn.dropout(tf.nn.leaky_relu(d2), 0.5)
d2 = tf.concat([d2, e5], 3)
d3 = ly.deconv2d(d2, 512, 8, strides=2,
name='g_deconv2d_3') # 8 * 8 * 512
d3 = ly.bn_layer(d3, name='g_bn_10')
d3 = tf.nn.dropout(tf.nn.leaky_relu(d3), 0.5)
d3 = tf.concat([d3, e4], 3)
d4 = ly.deconv2d(d3, 512, 16, strides=2,
name='g_deconv2d_4') # 16 * 16 * 512
d4 = ly.bn_layer(d4, name='g_bn_11')
d4 = tf.nn.leaky_relu(d4)
d4 = tf.concat([d4, e3], 3)
d5 = ly.deconv2d(d4, 256, 32, strides=2,
name='g_deconv2d_5') # 32 * 32 * 256
d5 = ly.bn_layer(d5, name='g_bn_12')
d5 = tf.nn.leaky_relu(d5)
d5 = tf.concat([d5, e2], 3)
d6 = ly.deconv2d(d5, 128, 64, strides=2,
name='g_deconv2d_6') # 64 * 64 * 128
d6 = ly.bn_layer(d6, name='g_bn_13')
d6 = tf.nn.leaky_relu(d6)
d6 = tf.concat([d6, e1], 3)
d7 = ly.deconv2d(d6, 64, 128, strides=2,
name='g_deconv2d_7') # 128 * 128 * 64
d7 = ly.bn_layer(d7, name='g_bn_14')
d7 = tf.nn.leaky_relu(d7)
d7 = tf.concat([d7, e0], 3)
d7 = ly.deconv2d(d7, 3, 256, strides=2,
name='g_deconv2d_8') # 256 * 256 * 3
d7 = tf.nn.tanh(d7)
return d7
def __call__(self, input):
### input --> image
### input_shape : [ -1, 128,128,3 ]
input_shape = input.get_shape().as_list()
input_channel = input_shape[-1]
with tf.variable_scope(self.name, reuse=self.reuse):
height = input.get_shape().as_list()[1]
### 提取特征 防止图片边缘奇异
input = tf.pad(input,
paddings=[[0, 0], [3, 3], [3, 3], [0, 0]],
mode='REFLECT')
input = ly.conv2d(input,
64,
kernel_size=7,
strides=1,
name='g_conv2d_0')
input = ly.bn_layer(input, name='g_bn_0')
input = tf.nn.relu(input)
input = ly.conv2d(input,
128,
kernel_size=3,
strides=2,
name='g_conv2d_1')
input = ly.bn_layer(input, name='g_bn_1')
input = tf.nn.relu(input)
input = ly.conv2d(input,
256,
kernel_size=3,
strides=2,
name='g_conv2d_2')
input = ly.bn_layer(input, name='g_bn_2')
input = tf.nn.relu(input)
### resnet
for i in range(8):
cell = ly.conv2d(input,
256,
kernel_size=3,
strides=1,
name='g_conv2d_res_%s' % i)
cell = ly.bn_layer(cell, name='g_res_%s' % i)
cell = tf.nn.relu(cell)
input = cell
low_height = math.ceil((height + 6.) / 4)
input = ly.deconv2d(input,
128,
low_height * 2,
kernel_size=3,
strides=2,
name='g_deconv2d_0')
input = ly.bn_layer(input, name='g_bn_3')
input = tf.nn.relu(input)
input = ly.deconv2d(input,
64,
low_height * 4,
kernel_size=3,
strides=2,
name='g_deconv2d_1')
input = ly.bn_layer(input, name='g_bn_4')
input = tf.nn.relu(input)
input = ly.conv2d(input,
3,
kernel_size=7,
strides=1,
name='g_conv2d_3')
input = ly.bn_layer(input, name='g_bn_5')
input = tf.nn.tanh(input)
input = tf.image.resize_images(input, [height, height])
self.reuse = True
return input