Bornlex

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.datasets import mnist

import numpy as np
from matplotlib import pyplot as plt

Bornlex

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train / 256
y_train = y_train / 256
np.random.shuffle(x_train)

Bornlex

LATENT_SIZE = 16

adam = keras.optimizers.Adam(lr=0.0002, beta_1=0.5)

with tf.device("/gpu:0"):
    input_x_img = keras.layers.Input((784,))
    x           = keras.layers.Dense(1024, activation="relu")(input_x_img)
    x           = keras.layers.Dense(256, activation="relu")(x)
    x           = keras.layers.Dense(1, activation="sigmoid")(x)
    discriminator = keras.models.Model(inputs=input_x_img, outputs=x)

Bornlex

EPOCHS       = 50
BATCH_SIZE   = 128
BATCH_BLOCKS = x_train.shape[0] // BATCH_SIZE

discriminator_losses = []
gan_losses           = []

for epoch in range(EPOCHS):
    for batch_index in range(BATCH_BLOCKS):
        batch         = x_train[batch_index * BATCH_SIZE:(batch_index + 1) * BATCH_SIZE].reshape(BATCH_SIZE, 784)