Create python-publish.yml

[Krysclick12]

No description provided.

[Krysclick12]

Update

[Krysclick12]

Update

[Krysclick12]

Chan g rfr``import tensorflow as tf
from tensorflow.keras import layers

Gather and preprocess the dataset

dataset = ...

Define the generator model

def build_generator():
model = tf.keras.Sequential()
model.add(layers.Dense(256, input_shape=(100,)))
model.add(layers.LeakyReLU(alpha=0.2))
model.add(layers.Dense(512))
model.add(layers.LeakyReLU(alpha=0.2))
model.add(layers.Dense(1024))
model.add(layers.LeakyReLU(alpha=0.2))
model.add(layers.Dense(784, activation='tanh'))
model.add(layers.Reshape((28, 28, 1)))
return model

generator = build_generator()

Define the discriminator model

def build_discriminator():
model = tf.keras.Sequential()
model.add(layers.Flatten(input_shape=(28, 28, 1)))
model.add(layers.Dense(512))
model.add(layers.LeakyReLU(alpha=0.2))
model.add(layers.Dense(256))
model.add(layers.LeakyReLU(alpha=0.2))
model.add(layers.Dense(1, activation='sigmoid'))
return model

discriminator = build_discriminator()

Define the loss function and optimizer

loss_fn = tf.keras.losses.BinaryCrossentropy(from_logits=True)
generator_optimizer = tf.keras.optimizers.Adam(1e-4)
discriminator_optimizer = tf.keras.optimizers.Adam(1e-4)

Train the generator and discriminator models

@tf.function
def train_step(real_images):
noise = tf.random.normal([BATCH_SIZE, 100])

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

    real_output = discriminator(real_images, training=True)
    generated_output = discriminator(generated_images, training=True)

    gen_loss = generator_loss(generated_output)
    disc_loss = discriminator_loss(real_output, generated_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))

Generate new graphic designs

def generate_designs(num_designs):
noise = tf.random.normal([num_designs, 100])
generated_images = generator(noise, training=False)
return generated_images

Example usage

num_designs = 10
generated_designs = generate_designs(num_designs)