Notes

import tensorflow as tf
from tensorflow.keras import layers
import numpy as np
import matplotlib.pyplot as plt

# Load and preprocess MNIST data
(train_images, _), (_, _) = tf.keras.datasets.mnist.load_data()
train_images = (train_images.astype(np.float32) - 127.5) / 127.5 # Normalize to [-1, 1]
train_images = np.expand_dims(train_images, axis=-1)
BUFFER_SIZE = 60000
BATCH_SIZE = 256

# Create datasets
train_dataset = tf.data.Dataset.from_tensor_slices(train_images).shuffle(BUFFER_SIZE).batch(BATCH_SIZE)

# Generator model
def build_generator():
model = tf.keras.Sequential()
model.add(layers.Dense(7*7*256, use_bias=False, input_shape=(100,)))
model.add(layers.BatchNormalization())
model.add(layers.LeakyReLU())

model.add(layers.Reshape((7, 7, 256)))
model.add(layers.Conv2DTranspose(128, (5, 5), strides=(1, 1), padding='same', use_bias=False))
model.add(layers.BatchNormalization())
model.add(layers.LeakyReLU())

model.add(layers.Conv2DTranspose(64, (5, 5), strides=(2, 2), padding='same', use_bias=False))
model.add(layers.BatchNormalization())
model.add(layers.LeakyReLU())

model.add(layers.Conv2DTranspose(1, (5, 5), strides=(2, 2), padding='same', use_bias=False, activation='tanh'))
return model

# Discriminator model
def build_discriminator():
model = tf.keras.Sequential()
model.add(layers.Conv2D(64, (5, 5), strides=(2, 2), padding='same', input_shape=[28, 28, 1]))
model.add(layers.LeakyReLU())
model.add(layers.Dropout(0.3))

model.add(layers.Conv2D(128, (5, 5), strides=(2, 2), padding='same'))
model.add(layers.LeakyReLU())
model.add(layers.Dropout(0.3))

model.add(layers.Flatten())
model.add(layers.Dense(1))
return model

# Loss function
cross_entropy = tf.keras.losses.BinaryCrossentropy(from_logits=True)

def discriminator_loss(real_output, fake_output):
real_loss = cross_entropy(tf.ones_like(real_output), real_output)
fake_loss = cross_entropy(tf.zeros_like(fake_output), fake_output)
total_loss = real_loss + fake_loss
return total_loss

def generator_loss(fake_output):
return cross_entropy(tf.ones_like(fake_output), fake_output)

# Optimizers
generator = build_generator()
discriminator = build_discriminator()

generator_optimizer = tf.keras.optimizers.Adam(1e-4)
discriminator_optimizer = tf.keras.optimizers.Adam(1e-4)

# Training
EPOCHS = 50
noise_dim = 100
num_examples_to_generate = 16

seed = tf.random.normal([num_examples_to_generate, noise_dim])

@tf.function
def train_step(images):
noise = tf.random.normal([BATCH_SIZE, noise_dim])

with tf.GradientTape() as gen_tape, tf.GradientTape() as disc_tape:
generated_images = generator(noise, training=True)

real_output = discriminator(images, training=True)
fake_output = discriminator(generated_images, training=True)

gen_loss = generator_loss(fake_output)
disc_loss = discriminator_loss(real_output, fake_output)

gradients_of_generator = gen_tape.gradient(gen_loss, generator.trainable_variables)
gradients_of_discriminator = disc_tape.gradient(disc_loss, discriminator.trainable_variables)

generator_optimizer.apply_gradients(zip(gradients_of_generator, generator.trainable_variables))
discriminator_optimizer.apply_gradients(zip(gradients_of_discriminator, discriminator.trainable_variables))


def train(dataset, epochs):
for epoch in range(epochs):
for image_batch in dataset:
train_step(image_batch)

# Produce images for the GIF
generate_and_save_images(generator, epoch + 1, seed)

print(f'Epoch {epoch + 1} completed')

def generate_and_save_images(model, epoch, test_input):
predictions = model(test_input, training=False)

fig = plt.figure(figsize=(4, 4))

for i in range(predictions.shape[0]):
plt.subplot(4, 4, i+1)
plt.imshow(predictions[i, :, :, 0] * 127.5 + 127.5, cmap='gray')
plt.axis('off')

plt.savefig(f'image_at_epoch_{epoch}.png')
plt.show()

# Start training
train(train_dataset, EPOCHS)