目录
一.生成器：
结构：
即一个修改过的U-Net网络，跳连在编码器和解码器之间。
编码器（下采样）的每个块由卷积层，batchnorm层和leakyrelu层构成；
解码器（上采样）的每个块由反卷积层，batchnorm层和Dropout层（仅应用于前三个块）构成。
代码：
OUTPUT_CHANNELS = 3
#编码器（下采样）
def downsample(filters, size, apply_batchnorm=True):
initializer = tf.random_normal_initializer(0., 0.02)
result = tf.keras.Sequential()
result.add(
tf.keras.layers.Conv2D(filters, size, strides=2, padding='same',
kernel_initializer=initializer, use_bias=False))
if apply_batchnorm:
result.add(tf.keras.layers.BatchNormalization())
result.add(tf.keras.layers.LeakyReLU())
return result
#down_model = downsample(3, 4)
#down_result = down_model(tf.expand_dims(inp, 0))
#print (down_result.shape)
##(1, 128, 128, 3)
########################################################
#上采样（解码器）
def upsample(filters, size, apply_dropout=False):
initializer = tf.random_normal_initializer(0., 0.02)
result = tf.keras.Sequential()
result.add(
tf.keras.layers.Conv2DTranspose(filters, size, strides=2,
padding='same',
kernel_initializer=initializer,
use_bias=False))
result.add(tf.keras.layers.BatchNormalization())
if apply_dropout:
result.add(tf.keras.layers.Dropout(0.5))
result.add(tf.keras.layers.ReLU())
return result
#up_model = upsample(3, 4)
#up_result = up_model(down_result)
#print (up_result.shape)
##(1, 256, 256, 3)
####################################################
#生成器
def Generator():
inputs = tf.keras.layers.Input(shape=[256, 256, 3])
down_stack = [
downsample(64, 4, apply_batchnorm=False), # (bs, 128, 128, 64)
downsample(128, 4), # (bs, 64, 64, 128)
downsample(256, 4), # (bs, 32, 32, 256)
downsample(512, 4), # (bs, 16, 16, 512)
downsample(512, 4), # (bs, 8, 8, 512)
downsample(512, 4), # (bs, 4, 4, 512)
downsample(512, 4), # (bs, 2, 2, 512)
downsample(512, 4), # (bs, 1, 1, 512)
]
up_stack = [
upsample(512, 4, apply_dropout=True), # (bs, 2, 2, 1024)
upsample(512, 4, apply_dropout=True), # (bs, 4, 4, 1024)
upsample(512, 4, apply_dropout=True), # (bs, 8, 8, 1024)
upsample(512, 4), # (bs, 16, 16, 1024)
upsample(256, 4), # (bs, 32, 32, 512)
upsample(128, 4), # (bs, 64, 64, 256)
upsample(64, 4), # (bs, 128, 128, 128)
]
initializer = tf.random_normal_initializer(0., 0.02)
last = tf.keras.layers.Conv2DTranspose(OUTPUT_CHANNELS, 4,
strides=2,
padding='same',
kernel_initializer=initializer,
activation='tanh') # (bs, 256, 256, 3)
x = inputs
# Downsampling through the model
skips = []
for down in down_stack:
x = down(x)
skips.append(x)
skips = reversed(skips[:-1])
# Upsampling and establishing the skip connections
for up, skip in zip(up_stack, skips):
x = up(x)
x = tf.keras.layers.Concatenate()([x, skip])
x = last(x)
return tf.keras.Model(inputs=inputs, outputs=x)
如图：
生成器损失：
（1）生成的图像和元素为1的张量间的叉熵损失
（2）生成的图像和真实图像L1，
这使得生成图像结构上和真实图像相似。
总LAMBDA=100，total generator loss = gan_loss + LAMBDA * l1_loss
代码：
LAMBDA = 100
loss_object = tf.keras.losses.BinaryCrossentropy(from_logits=True)
#计算真实标签和预测标签之间的交叉熵损失
#当只有两个标签类(假设为0和1)时，使用这个交叉熵损失。对于每个示例，每个预测都应该有一个浮点值
def generator_loss(disc_generated_output, gen_output, target):
gan_loss = loss_object(tf.ones_like(disc_generated_output), disc_generated_output)
# mean absolute error
l1_loss = tf.reduce_mean(tf.abs(target - gen_output))
total_gen_loss = gan_loss + (LAMBDA * l1_loss)
return total_gen_loss, gan_loss, l1_loss如图：
二.判别器：
结构：
判别器使用的所谓的patchGAN结构，由patchGAN得到的30*30*1的输出对应
它首先将输入图（256,256,3）和目标（或者生成）图（256,256,256,3）在channel维度上合在一起（256,256,6），然后进行三次下采样（32,32,32,256），一次padding后（34,34,34,256）,再依次使用卷积（31*31*512）、BN（31*31*512），LeakyRelu（31*31*512）、padding（33*33*512）、卷积（30*30*1），得到一个30*30*1的输出。
注：如果输入图像和目标图像送入判别器，应被判为真；如果输入图像和生成图像送入判别器，最后应判别为假。
代码：
def Discriminator():
initializer = tf.random_normal_initializer(0., 0.02)
inp = tf.keras.layers.Input(shape=[256, 256, 3], name='input_image')
tar = tf.keras.layers.Input(shape=[256, 256, 3], name='target_image')
x = tf.keras.layers.concatenate([inp, tar]) # (bs, 256, 256, channels*2)
down1 = downsample(64, 4, False)(x) # (bs, 128, 128, 64)
down2 = downsample(128, 4)(down1) # (bs, 64, 64, 128)
down3 = downsample(256, 4)(down2) # (bs, 32, 32, 256)
zero_pad1 = tf.keras.layers.ZeroPadding2D()(down3) # (bs, 34, 34, 256)
conv = tf.keras.layers.Conv2D(512, 4, strides=1,
kernel_initializer=initializer,
use_bias=False)(zero_pad1) # (bs, 31, 31, 512)
batchnorm1 = tf.keras.layers.BatchNormalization()(conv)
leaky_relu = tf.keras.layers.LeakyReLU()(batchnorm1)
zero_pad2 = tf.keras.layers.ZeroPadding2D()(leaky_relu) # (bs, 33, 33, 512)
last = tf.keras.layers.Conv2D(1, 4, strides=1,
kernel_initializer=initializer)(zero_pad2) # (bs, 30, 30, 1)
return tf.keras.Model(inputs=[inp, tar], outputs=last)如图：
判别器损失：
判别损失函数有两个输入，真的图像和假的图像。
总损失由两部分和构成：real_loss + generated_loss。其中real_loss为真实图像和元素为1的张量间的交叉熵损失； generated_loss为生成图像和元素为0的张量间的交叉熵损失
代码：
def discriminator_loss(disc_real_output, disc_generated_output):
real_loss = loss_object(tf.ones_like(disc_real_output), disc_real_output)
generated_loss = loss_object(tf.zeros_like(disc_generated_output), disc_generated_output)
total_disc_loss = real_loss + generated_loss
return total_disc_loss如图：