T e n s o r f l o w 实 现 D C G A N Tensorflow实现DCGAN Tensorflow实现DCGAN

使用DCGAN生成动漫人物头像

  • DCGAN就是将CNN和原始的GAN结合到了一起， 生成模型和判别模型都运用了深度卷积神经网络的生 成对抗网络

Unsupervised Representation Learning with DeepConvolutional Generative Adversarial Networks

  • DCGAN对卷积神经网络的结构做了一些改变，以提高样本的质量和收敛的速度。

Tensorflow实现DCGAN_激活函数

  • 一、取消所有pooling层。G网络中使用转置卷积(transposed convolutional layer)进行上采样，D网络中用加入stride的卷积代替 pooling。

  • 二、去掉FC层，使网络变为全卷积网络

  • 三、G网络中使用ReLU作为激活函数，最后一层使用tanh

  • 四、D网络中使用L eakyReLU作为激活函数

  • 五、在generator和discriminator 上都使用batchnorm
    解决初始化差的问题
    帮助梯度传播到每一层
    防止generator把所有的样本都收敛到同一个点。
    直接将BN应用到所有层会导致样本震荡和模型不稳定，通过在generator输出层和discriminator输入层不采用BN可以防止这种现象。

  • 六、使用Adam优化器,
    beta1(一阶矩估计的指数衰减率)的值设置为0.5

  • 七、论文参数
    LeakyReLU的斜率是0.2.
    learning rate =0.0002
    batch size是128.

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import glob
import os
tf.keras.backend.clear_session() 
(train_images, train_labels), (_, _) = tf.keras.datasets.mnist.load_data()

train_images = train_images.reshape(train_images.shape[0], 28, 28, 1).astype('float32')
train_images = (train_images - 127.5) / 127.5 # Normalize the images to [-1, 1]

BUFFER_SIZE = 60000
BATCH_SIZE = 256

# Batch and shuffle the data
train_dataset = tf.data.Dataset.from_tensor_slices(train_images).shuffle(BUFFER_SIZE).batch(BATCH_SIZE)

def generator_model():
    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)))
    assert model.output_shape == (None, 7, 7, 256) # Note: None is the batch size

    model.add(layers.Conv2DTranspose(128, (5, 5), strides=(1, 1), padding='same', use_bias=False))
    assert model.output_shape == (None, 7, 7, 128)
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

    model.add(layers.Conv2DTranspose(64, (5, 5), strides=(2, 2), padding='same', use_bias=False))
    assert model.output_shape == (None, 14, 14, 64)
    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'))
    assert model.output_shape == (None, 28, 28, 1)

    return model

def discriminator_model():
    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

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.ones_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)*0.9, fake_output)

generator_optimizer = tf.keras.optimizers.Adam(1e-5)
discriminator_optimizer = tf.keras.optimizers.Adam(1e-5)

EPOCHS = 50
noise_dim = 100
num_examples_to_generate = 16

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

generator = generator_model()
discriminator = discriminator_model()

@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 generate_and_save_images(model, epoch, test_input):
  # Notice `training` is set to False.
  # This is so all layers run in inference mode (batchnorm).
    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] + 1)/2, cmap='gray')
        plt.axis('off')

    plt.savefig('image_at_epoch_{:04d}.png'.format(epoch))
    plt.show()

def train(dataset, epochs):
    for epoch in range(epochs):
        for image_batch in dataset:
            train_step(image_batch)
            print('.', end='')
        print()

        generate_and_save_images(generator,
                             epoch + 1,
                             seed)


    generate_and_save_images(generator,
                           epochs,
                           seed)

train(train_dataset, EPOCHS)