GAN的实现

#导入包和数据集
%matplotlib inline
import pickle as pkl
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data' 

模型输入

def model_inputs(real_dim, z_dim):
    inputs_real = tf.placeholder(tf.float32,(None ,real_dim),name ='input_real')
    inputs_z = tf.placeholder(tf.float32,(None,z_dim),name = 'input_z') 
    return inputs_real, inputs_z

生成器

def generator(z, out_dim, n_units=128, reuse=False,  alpha=0.01):
    ''' Build the generator network.
    
        Arguments
        ---------
        z : Input tensor for the generator
        out_dim : Shape of the generator output
        n_units : Number of units in hidden layer
        reuse : Reuse the variables with tf.variable_scope
        alpha : leak parameter for leaky ReLU
        
        Returns
        -------
        out, logits: 
    '''
    with tf.variable_scope('generator',reuse = reuse) :
        # Hidden layer
        h1 = tf.layers.dense(z,n_units,activation = None)
        # Leaky ReLU
        h1 = tf.maximum(alpha * h1,h1)
        
        # Logits and tanh output
        logits = tf.layers.dense(h1,out_dim)
        out = tf.tanh(logits)
        
        return out

判别器

def discriminator(x, n_units=128, reuse=False, alpha=0.01):
    ''' Build the discriminator network.
    
        Arguments
        ---------
        x : Input tensor for the discriminator
        n_units: Number of units in hidden layer
        reuse : Reuse the variables with tf.variable_scope
        alpha : leak parameter for leaky ReLU
        
        Returns
        -------
        out, logits: 
    '''
    with tf.variable_scope('discriminator',reuse = reuse):
        # Hidden layer
        h1 =tf.layers.dense(x,n_units,activation = None)
        # Leaky ReLU
        h1 =tf.maximum(alpha * h1,h1)
        
        logits = tf.layers.dense(h1,1,activation = None)
        out =tf.sigmod(logits)
        
        return out, logits

超参数

# Size of input image to discriminator
input_size = 784 # 28x28 MNIST images flattened
# Size of latent vector to generator
z_size = 100
# Sizes of hidden layers in generator and discriminator
g_hidden_size = 128
d_hidden_size = 128
# Leak factor for leaky ReLU
alpha = 0.01
# Label smoothing 
smooth = 0.1

构建网络

tf.reset_default_graph()
# Create our input placeholders
input_real, input_z = model_inputs(input_size, z_size)

# Build the model
g_model = generator(input_z, input_size)
# g_model is the generator output

d_model_real, d_logits_real = discriminator(input_real)
d_model_fake, d_logits_fake = discriminator(g_model, reuse=True)

计算辨别器及生成器的损失

# Calculate losses
d_loss_real = tf.reduce_mean(
                  tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_real, 
                                                          labels=tf.ones_like(d_logits_real) * (1 - smooth)))
d_loss_fake = tf.reduce_mean(
                  tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake, 
                                                          labels=tf.zeros_like(d_logits_real)))
d_loss = d_loss_real + d_loss_fake

g_loss = tf.reduce_mean(
             tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake,
                                                     labels=tf.ones_like(d_logits_fake)))

优化器

# Optimizers
learning_rate = 0.002

# Get the trainable_variables, split into G and D parts
t_vars = tf.trainable_variables()
g_vars = [var for var in t_vars if var.name.startswith('generator')]
d_vars = [var for var in t_vars if var.name.startswith('discriminator')]

d_train_opt = tf.train.AdamOptimizer(learning_rate).minimize(d_loss, var_list=d_vars)
g_train_opt = tf.train.AdamOptimizer(learning_rate).minimize(g_loss, var_list=g_vars)

训练

batch_size = 100
epochs = 100
samples = []
losses = []
# Only save generator variables
saver = tf.train.Saver(var_list=g_vars)
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for e in range(epochs):
        for ii in range(mnist.train.num_examples//batch_size):
            batch = mnist.train.next_batch(batch_size)
            
            # Get images, reshape and rescale to pass to D
            batch_images = batch[0].reshape((batch_size, 784))
            batch_images = batch_images*2 - 1
            
            # Sample random noise for G
            batch_z = np.random.uniform(-1, 1, size=(batch_size, z_size))
            
            # Run optimizers
            _ = sess.run(d_train_opt, feed_dict={input_real: batch_images, input_z: batch_z})
            _ = sess.run(g_train_opt, feed_dict={input_z: batch_z})
        
        # At the end of each epoch, get the losses and print them out
        train_loss_d = sess.run(d_loss, {input_z: batch_z, input_real: batch_images})
        train_loss_g = g_loss.eval({input_z: batch_z})
            
        print("Epoch {}/{}...".format(e+1, epochs),
              "Discriminator Loss: {:.4f}...".format(train_loss_d),
              "Generator Loss: {:.4f}".format(train_loss_g))    
        # Save losses to view after training
        losses.append((train_loss_d, train_loss_g))
        
        # Sample from generator as we're training for viewing afterwards
        sample_z = np.random.uniform(-1, 1, size=(16, z_size))
        gen_samples = sess.run(
                       generator(input_z, input_size, reuse=True),
                       feed_dict={input_z: sample_z})
        samples.append(gen_samples)
        saver.save(sess, './checkpoints/generator.ckpt')

# Save training generator samples
with open('train_samples.pkl', 'wb') as f:
    pkl.dump(samples, f)