Question

对于此代码：

     # Initialize generator - feed noise and profile images
noise = random_normal(shape = (-1, 8, 8, z_dim), mean = 0.0, stddev = 1.0, dtype = None, seed = None)

noise      = Input(tensor = noise)
input_data = Input(shape = (128, 128, 3))

generated_img = generator_network(input_data, noise)

# Initialize discriminator - feed frontal faces as ground truth and the generated images as fake
generated_img = Input(tensor = generated_img)

true_score = discriminator_network(input_data)
fake_score = discriminator_network(generated_img)

# Optimizer
Adam_optimizer = Adam(lr = learning_rate, beta_1 = 0.9, beta_2 = 0.999, epsilon = 1e-08, decay = decay_rate)

# Losses
discrim_loss = discriminator_loss(true_score, fake_score)
var_loss     = variation_loss(input_data, generated_img)
pix_loss     = pixel_loss(input_data, generated_img)
cross_loss   = cross_entropy_loss(true_score, fake_score)
gen_loss     = generator_loss(discrim_loss, var_loss, pix_loss, cross_loss)

# Models
discriminator = Model(inputs = generated_img      , outputs = fake_score)
generator     = Model(inputs = [input_data, noise], outputs = generated_img)

# Compilers
discriminator.compile(optimizer = Adam_optimizer, loss = discriminator_loss)
generator.compile(    optimizer = Adam_optimizer, loss = generator_loss)

我收到此错误：

追踪（最近一次通话）：文件“main.py”，第74行，in generator = Model（inputs = [input_data，noise]，outputs = generated_img）在包装器中输入文件“/home/diana/Documents/VirtualNN/local/lib/python2.7/site-packages/keras/legacy/interfaces.py”，第87行 return func（* args，** kwargs）在 init 中输入文件“/home/diana/Documents/VirtualNN/local/lib/python2.7/site-packages/keras/engine/topology.py”，第1793行 STR（layers_with_complete_input）） RuntimeError：Graph disconnected：无法在层“input_3”获取张量Tensor（“conv2d_35 / Relu：0”，shape =（？，？，？，3），dtype = float32）的值。访问以下先前的图层时没有问题：[]

有谁知道为什么它说我的模型生成器不是连接图？根据我的理解，它是相互联系的。但也许还有其他一些我看不到的东西。

Answer 1

如果您的目的是构建GAN模型，则应将生成器网络和鉴别器网络包装为另一个网络中的两个连续层。例如：

from keras.models import Sequential

# generator_network() and generator_network() should each have an Input layer 
#   that defines their input shapes respectively
g_network = generator_network()
d_network = discriminator_network()

gan_network = Sequential()
gan_network.add(g_network)
d_network.trainable = False
gan_network.add(d_network)

# Compilers
d_network.compile(optimizer = Adam_optimizer, loss = discriminator_loss)
gan_network.compile(optimizer = Adam_optimizer, loss = generator_loss)

Keras中GAN的断开连接图

1 个答案: