DCGAN的实现

导入数据与模块

%matplotlib inline

import pickle as pkl

import matplotlib.pyplot as plt
import numpy as np
from scipy.io import loadmat
import tensorflow as tf

network inputs

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

generator

def generator(z, output_dim, reuse=False, alpha=0.2, training=True):
    with tf.variable_scope('generator', reuse=reuse):
        # First fully connected layer
        x1 = tf.layers.dense(z, 4*4*512)
        # Reshape it to start the convolutional stack
        x1 = tf.reshape(x1, (-1, 4, 4, 512))
        x1 = tf.layers.batch_normalization(x1, training=training)
        x1 = tf.maximum(alpha * x1, x1)
        # 4x4x512 now
        
        x2 = tf.layers.conv2d_transpose(x1, 256, 5, strides=2, padding='same')
        x2 = tf.layers.batch_normalization(x2, training=training)
        x2 = tf.maximum(alpha * x2, x2)
        # 8x8x256 now，卷积核大小设为5*5
        
        x3 = tf.layers.conv2d_transpose(x2, 128, 5, strides=2, padding='same')
        x3 = tf.layers.batch_normalization(x3, training=training)
        x3 = tf.maximum(alpha * x3, x3)
        # 16x16x128 now
        
        # Output layer
        logits = tf.layers.conv2d_transpose(x3, output_dim, 5, strides=2, padding='same')
        # 32x32x3 now
        
        out = tf.tanh(logits)
        
        return out

discriminator

def discriminator(x, reuse=False, alpha=0.2):
    with tf.variable_scope('discriminator', reuse=reuse):
        # Input layer is 32x32x3
        x1 = tf.layers.conv2d(x, 64, 5, strides=2, padding='same')
        relu1 = tf.maximum(alpha * x1, x1)
        # 16x16x64
        
        x2 = tf.layers.conv2d(relu1, 128, 5, strides=2, padding='same')
        bn2 = tf.layers.batch_normalization(x2, training=True)
        relu2 = tf.maximum(alpha * bn2, bn2)
        # 8x8x128
        
        x3 = tf.layers.conv2d(relu2, 256, 5, strides=2, padding='same')
        bn3 = tf.layers.batch_normalization(x3, training=True)
        relu3 = tf.maximum(alpha * bn3, bn3)
        # 4x4x256

        # Flatten it
        flat = tf.reshape(relu3, (-1, 4*4*256))
        logits = tf.layers.dense(flat, 1)
        out = tf.sigmoid(logits)
        
        return out, logits

model loss

def model_loss(input_real, input_z, output_dim, alpha=0.2):
    """
    Get the loss for the discriminator and generator
    :param input_real: Images from the real dataset
    :param input_z: Z input
    :param out_channel_dim: The number of channels in the output image
    :return: A tuple of (discriminator loss, generator loss)
    """
    g_model = generator(input_z, output_dim, alpha=alpha)
    d_model_real, d_logits_real = discriminator(input_real, alpha=alpha)
    d_model_fake, d_logits_fake = discriminator(g_model, reuse=True, alpha=alpha)

    d_loss_real = tf.reduce_mean(
        tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_real, labels=tf.ones_like(d_model_real)))
    d_loss_fake = tf.reduce_mean(
        tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake, labels=tf.zeros_like(d_model_fake)))
    g_loss = tf.reduce_mean(
        tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake, labels=tf.ones_like(d_model_fake)))

    d_loss = d_loss_real + d_loss_fake

    return d_loss, g_loss

optimiters

def model_opt(d_loss, g_loss, learning_rate, beta1):
    """
    Get optimization operations
    :param d_loss: Discriminator loss Tensor
    :param g_loss: Generator loss Tensor
    :param learning_rate: Learning Rate Placeholder
    :param beta1: The exponential decay rate for the 1st moment in the optimizer
    :return: A tuple of (discriminator training operation, generator training operation)
    """
    # Get weights and bias to update
    t_vars = tf.trainable_variables()
    d_vars = [var for var in t_vars if var.name.startswith('discriminator')]
    g_vars = [var for var in t_vars if var.name.startswith('generator')]

    # Optimize
    with tf.control_dependencies(tf.get_collection(tf.GraphKeys.UPDATE_OPS)):
        d_train_opt = tf.train.AdamOptimizer(learning_rate, beta1=beta1).minimize(d_loss, var_list=d_vars)
        g_train_opt = tf.train.AdamOptimizer(learning_rate, beta1=beta1).minimize(g_loss, var_list=g_vars)

    return d_train_opt, g_train_opt

train的代码与我的上一篇类似，接下来会实战DCGAN生成人脸图像