descriminator.py

import tensorflow as tf
from tensorflow.keras import layers


def make_discriminator_model():
    model = tf.keras.Sequential()
    model.add(layers.Conv2D(64, (5, 5), strides=(2, 2), padding='same', input_shape=[64, 64, 3]))
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

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

    model.add(layers.Conv2D(256, (5, 5), strides=(2, 2), padding='same'))
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

    model.add(layers.Conv2D(512, (5, 5), strides=(2, 2), padding='same'))
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

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

    return model


def make_discriminator_model_big():
    model = tf.keras.Sequential()

    model.add(layers.Conv2D(128, (5, 5), strides=(2, 2), padding='same', input_shape=[128, 128, 3]))
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

    model.add(layers.Conv2D(256, (5, 5), strides=(2, 2), padding='same'))
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

    model.add(layers.Conv2D(512, (5, 5), strides=(2, 2), padding='same'))
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

    model.add(layers.Conv2D(1024, (5, 5), strides=(2, 2), padding='same'))
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

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

    return model


def discriminator_loss(real_output, fake_output):
    cross_entropy = tf.keras.losses.BinaryCrossentropy(from_logits=True)
    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