GAN не очень хорошо продолжает обучение

Я запрограммировал модель GAN с использованием keras, но обучение прошло не очень хорошо. Модель генератора всегда возвращает чистое изображение шума (размером 28x28) вместо чего-то похожего на набор данных mnist. Это не дает мне никаких ошибок, когда дело доходит до обучения модели дискриминатора становится trainable=False, что я не хочу делать.

Если эта реализация плохая, дайте мне знать. Кто-нибудь может помочь?

import os
import numpy as np
import matplotlib.pyplot as plt
import keras
from keras.models import Sequential
from keras.layers import Dense, Activation, BatchNormalization
from keras.optimizers import SGD, Adam, RMSprop
from keras.datasets import mnist
from keras.regularizers import l1_l2

def plot_generated(noise, Generator):
    image_fake = Generator.predict(noise)
    plt.figure(figsize=(10,8))
    plt.show()
    plt.close()

def plot_metircs(metrics, epoch=None):
    plt.figure(figsize=(10,8))
    plt.plot(metrics['d'], label='discriminative loss', color='b')
    plt.legend()
    plt.show()
    plt.close()

    plt.figure(figsize=(10,8))
    plt.plot(metrics['g'], label='generative loss', color='r')
    plt.legend()
    plt.show()
    plt.close()

def Generator():
    model = Sequential()
    LeakyReLU = keras.layers.advanced_activations.LeakyReLU(alpha=0.2)
    model.add(Dense(input_dim=100, units=128, activation=LeakyReLU, name='g_input'))
    model.add(Dense(input_dim=128, units=784, activation='tanh', name='g_output'))
    return model

def Discriminator():
    model = Sequential()
    LeakyReLU = keras.layers.advanced_activations.LeakyReLU(alpha=0.2)
    model.add(Dense(input_dim=784, units=128, activation=LeakyReLU, name='d_input'))
    model.add(Dense(input_dim=128, units=1, activation='sigmoid', name='d_output'))
    model.compile(loss='binary_crossentropy', optimizer='Adam')
    return model

def Generative_Adversarial_Network(Generator, Discriminator):
    model = Sequential()
    model.add(Generator)
    model.add(Discriminator)
    # train only generator in the entire GAN architecture
    Discriminator.trainable = False
    model.compile(loss='binary_crossentropy', optimizer='Adam')
    return model

def Training(z_input_size, Generator, Discriminator, GAN, loss_dict, X_train, epoch, batch, smooth):
    for e in range(epoch):
        # z: noise, used for input of G to generate fake image based on this noise! it's like a seed 
        noise = np.random.uniform(-1, 1, size=[batch, z_input_size])
        image_fake = Generator.predict_on_batch(noise)

        # sampled real_image from dataset
        rand_train_index = np.random.randint(0, X_train.shape[0], size=batch)
        image_real = X_train[rand_train_index, :]

        # concatenate real and fake images
        """
        X = [
            image_real => label : 1 (we can multiply a smoothing factor)
            image_fake => label : 0
            ]
        """
        X = np.vstack((image_real, image_fake))
        y = np.zeros(len(X))

        # putting label "1" to image_real
        y[len(image_real):] = 1*(1 - smooth)
        y = y.astype(int)

        # train only discriminator
        d_loss = Discriminator.train_on_batch(x=X, y=y)

        # NOTE: remember?? we set discriminator OFF during the training of GAN!
        # So, we can safely train only generator, weight of discriminator set fixed!
        g_loss = GAN.train_on_batch(x=noise, y=y[len(noise):])

        loss_dict['d'].append(d_loss)
        loss_dict['g'].append(g_loss)

        if e%1000 == 0:
            plt.imshow(image_fake)
            plt.show()
            plot_generated(noise, Generator)

    plot_metircs(loss_dict)
    return "done!"


Gen = Generator()
Dis = Discriminator()
GAN = Generative_Adversarial_Network(Gen, Dis)
GAN.summary()
Gen.summary()
Dis.summary()

gan_losses = {"d":[], "g":[], "f":[]}
epoch = 30000
batch = 1000
smooth = 0.9
z_input_size = 100
row, col = 28, 28

z_group_matrix = np.random.uniform(0, 1, examples*z_input_size)
z_group_matrix = z_group_matrix.reshape([9, z_input_size])
print(z_group_matrix.shape)

(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train, X_test = X_train.reshape(X_train.shape[0], row*col), X_test.reshape(X_test.shape[0], row*col)
X_train.astype('float32')
X_test.astype('float32')
X_train, X_test = X_train/255, X_test/255
print('X_train shape: ', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')

Training(z_input_size, Gen, Dis, GAN, loss_dict=gan_losses, X_train=X_train, epoch=epoch, batch=batch, smooth=smooth)