有条件的甘训练题

如何解决有条件的甘训练题

我使用了来自 (http://vision.ucsd.edu/~leekc/ExtYaleDatabase/ExtYaleB.html) 的数据集并想用 Conditional gan 生成人脸图像，我参考了 (https://github.com/GANs-in-Action/gans-in-action/blob/master/chapter-8/Chapter_8_CGAN.ipynb) 和 (https://github.com/ mvedang/Conditional-GAN -CIFAR-10) 网络架构，但无论我训练多少次，得到的图像仍然是噪声。

即使我调整了 discriminator 和 Generator 的参数，如层、神经元等，生成的结果仍然是噪声。

你能帮我更正我构建的生成器和判别器模型吗？ 代码和结果链接：https://colab.research.google.com/drive/14ul6BeXpVnlO3TVmfvSiR0kkYUuWfvn-?usp=sharing

Generator ：

double d1 = 0d;
double d2 = 0d;

Discriminator：

def build_cgan_generator(z_dim):
    z_input = Input(shape=(z_dim,))
    label_input = Input(shape=(1,),dtype='int32')
    label_embedding = Embedding(classes,output_dim=z_dim,input_length=1)(label_input)
    label_embedding = Flatten()(label_embedding)
    join_represent = Multiply()([z_input,label_embedding])

    x = Dense(4*4*256)(join_represent)
    x = Reshape((4,4,256))(x)#4*4*256

    x = Conv2DTranspose(64,kernel_size=3,padding='same',strides=2)(x)#8*8*64
    #x = Batchnormalization(momentum=0.8)(x)
    x = LeakyReLU(0.01)(x)

    x = Conv2DTranspose(128,strides=2)(x)#16*16*128
    #x = Batchnormalization(momentum=0.8)(x)
    x = LeakyReLU(0.01)(x)

    x = Conv2DTranspose(64,strides=2)(x)#32*32*64
    #x = Batchnormalization(momentum=0.8)(x)
    x = LeakyReLU(0.01)(x)

    x = Conv2DTranspose(32,strides=2)(x)#64*64*32
    #x = Batchnormalization(momentum=0.8)(x)
    x = LeakyReLU(0.01)(x)
    
    x = Conv2DTranspose(3,kernel_size=4,strides=2)(x)#128*128*3

    output = keras.layers.Activation('tanh')(x)

    model = keras.Model([z_input,label_input],output)
    tf.keras.utils.plot_model(model,to_file='generator.png',show_shapes=True)
    return model