Deep interesting | 08 DCGAN face image generated

Introduction to the

We train DCGAN on face data and generate some face pictures

data

Use two data sets

LFW: Vis-www.cs.umass.edu/lfw/, Labeled Faces in the Wild, over 1.3W images, 1680 of whom had more than two or more images
CelebA:mmlab.ie.cuhk.edu.hk/projects/Ce… , CelebFaces Attributes Dataset, which includes more than 20W images of 10177 people, and each image also includes 5 key positions of face and 01 annotation of 40 Attributes, such as glasses, hat, beard, etc

implementation

Same code as last lesson, according to the color picture can be adjusted appropriately

Load the library

# -*- coding: utf-8 -*-

import tensorflow as tf
import numpy as np
import urllib
import tarfile
import os
import matplotlib.pyplot as plt
%matplotlib inline
from imageio import imread, imsave, mimsave
from scipy.misc import imresize
import glob
Copy the code

Download LFW data and decompress it. CelebA data is ready

url = 'http://vis-www.cs.umass.edu/lfw/lfw.tgz'
filename = 'lfw.tgz'
directory = 'lfw_imgs'
new_dir = 'lfw_new_imgs'

if not os.path.isdir(new_dir):
    os.mkdir(new_dir)
    
    if not os.path.isdir(directory):
        if not os.path.isfile(filename):
            urllib.request.urlretrieve(url, filename)
        tar = tarfile.open(filename, 'r:gz')
        tar.extractall(path=directory)
        tar.close()
    
    count = 0
    for dir_, _, files in os.walk(directory):
        for file_ in files:
            img = imread(os.path.join(dir_, file_))
            imsave(os.path.join(new_dir, '%d.png' % count), img)
            count += 1
Copy the code

Sets the data set used to generate the face

# dataset = 'lfw_new_imgs' # LFW
dataset = 'celeba' # CelebA
images = glob.glob(os.path.join(dataset, '*. *')) 
print(len(images))
Copy the code

Define constants, network inputs, and helper functions

batch_size = 100
z_dim = 100
WIDTH = 64
HEIGHT = 64

OUTPUT_DIR = 'samples_' + dataset
if not os.path.exists(OUTPUT_DIR):
    os.mkdir(OUTPUT_DIR)

X = tf.placeholder(dtype=tf.float32, shape=[None, HEIGHT, WIDTH, 3], name='X')
noise = tf.placeholder(dtype=tf.float32, shape=[None, z_dim], name='noise')
is_training = tf.placeholder(dtype=tf.bool, name='is_training') def lrelu (x, leak = 0.2) :return tf.maximum(x, leak * x)

def sigmoid_cross_entropy_with_logits(x, y):
    return tf.nn.sigmoid_cross_entropy_with_logits(logits=x, labels=y)
Copy the code

Discriminator part

Def discriminator(image, reuse=None, is_training=is_training): momentum = 0.9 with tf.variable_scope()'discriminator', reuse=reuse):
        h0 = lrelu(tf.layers.conv2d(image, kernel_size=5, filters=64, strides=2, padding='same'))
        
        h1 = tf.layers.conv2d(h0, kernel_size=5, filters=128, strides=2, padding='same')
        h1 = lrelu(tf.contrib.layers.batch_norm(h1, is_training=is_training, decay=momentum))
        
        h2 = tf.layers.conv2d(h1, kernel_size=5, filters=256, strides=2, padding='same')
        h2 = lrelu(tf.contrib.layers.batch_norm(h2, is_training=is_training, decay=momentum))
        
        h3 = tf.layers.conv2d(h2, kernel_size=5, filters=512, strides=2, padding='same')
        h3 = lrelu(tf.contrib.layers.batch_norm(h3, is_training=is_training, decay=momentum))
        
        h4 = tf.contrib.layers.flatten(h3)
        h4 = tf.layers.dense(h4, units=1)
        return tf.nn.sigmoid(h4), h4
Copy the code

Generator section

Def generator(z, is_training=is_training): momentum = 0.9 with tf.variable_scope('generator', reuse=None):
        d = 4
        h0 = tf.layers.dense(z, units=d * d * 512)
        h0 = tf.reshape(h0, shape=[-1, d, d, 512])
        h0 = tf.nn.relu(tf.contrib.layers.batch_norm(h0, is_training=is_training, decay=momentum))
        
        h1 = tf.layers.conv2d_transpose(h0, kernel_size=5, filters=256, strides=2, padding='same')
        h1 = tf.nn.relu(tf.contrib.layers.batch_norm(h1, is_training=is_training, decay=momentum))
        
        h2 = tf.layers.conv2d_transpose(h1, kernel_size=5, filters=128, strides=2, padding='same')
        h2 = tf.nn.relu(tf.contrib.layers.batch_norm(h2, is_training=is_training, decay=momentum))
        
        h3 = tf.layers.conv2d_transpose(h2, kernel_size=5, filters=64, strides=2, padding='same')
        h3 = tf.nn.relu(tf.contrib.layers.batch_norm(h3, is_training=is_training, decay=momentum))
        
        h4 = tf.layers.conv2d_transpose(h3, kernel_size=5, filters=3, strides=2, padding='same', activation=tf.nn.tanh, name='g')
        return h4
Copy the code

Loss function

g = generator(noise)
d_real, d_real_logits = discriminator(X)
d_fake, d_fake_logits = discriminator(g, reuse=True)

vars_g = [var for var in tf.trainable_variables() if var.name.startswith('generator')]
vars_d = [var for var in tf.trainable_variables() if var.name.startswith('discriminator')]

loss_d_real = tf.reduce_mean(sigmoid_cross_entropy_with_logits(d_real_logits, tf.ones_like(d_real)))
loss_d_fake = tf.reduce_mean(sigmoid_cross_entropy_with_logits(d_fake_logits, tf.zeros_like(d_fake)))
loss_g = tf.reduce_mean(sigmoid_cross_entropy_with_logits(d_fake_logits, tf.ones_like(d_fake)))
loss_d = loss_d_real + loss_d_fake
Copy the code

Optimization function

update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS) with tf.control_dependencies(update_ops): Optimizer_d = tf. Train. AdamOptimizer (learning_rate = 0.0002, beta1 = 0.5). Minimize (loss_d, Var_list =vars_d) optimizer_g = tf.train.adamoptimizer (learning_rate=0.0002, beta1=0.5). Minimize (loss_g, var_list=vars_g)Copy the code

The function that reads the picture

def read_image(path, height, width):
    image = imread(path)
    h = image.shape[0]
    w = image.shape[1]
    
    if h > w:
        image = image[h // 2 - w // 2: h // 2 + w // 2, :, :]
    else:
        image = image[:, w // 2 - h // 2: w // 2 + h // 2, :]    
    
    image = imresize(image, (height, width))
    return image / 255.
Copy the code

The function that synthesizes the picture

def montage(images):    
    if isinstance(images, list):
        images = np.array(images)
    img_h = images.shape[1]
    img_w = images.shape[2]
    n_plots = int(np.ceil(np.sqrt(images.shape[0])))
    iflen(images.shape) == 4 and images.shape[3] == 3: M = np.ones((images.shape[1] * n_plots + n_plots + 1, images.shape[2] * n_plots + n_plots + 1, 3)) * 0.5eliflen(images.shape) == 4 and images.shape[3] == 1: M = np.ones((images.shape[1] * n_plots + n_plots + 1, images.shape[2] * n_plots + n_plots + 1, 1)) * 0.5eliflen(images.shape) == 3: M = np.ones((images.shape[1] * n_plots + n_plots + 1, images.shape[2] * n_plots + n_plots + 1)) * 0.5else:
        raise ValueError('Could not parse image shape of {}'.format(images.shape))
    for i in range(n_plots):
        for j in range(n_plots):
            this_filter = i * n_plots + j
            if this_filter < images.shape[0]:
                this_img = images[this_filter]
                m[1 + i + i * img_h:1 + i + (i + 1) * img_h,
                  1 + j + j * img_w:1 + j + (j + 1) * img_w] = this_img
    return m
Copy the code

Model training

Sess = tf.session () sess.run(tf.global_variables_initializer()) z_samples = Np.random. Uniform (-1.0, 1.0, [batch_size, z_dim]).astype(np.float32) samples = [] loss = {'d': [].'g': []}

offset = 0
for i inrange(60000): N = np.random. Uniform (-1.0, 1.0, [batch_size, z_dim]).astype(np.float32) offset = (offset + batch_size) % len(images) batch = np.array([read_image(img, HEIGHT, WIDTH)for img inImages [offset: offset + batch_size]]) Batch = (batch-0.5) * 2 d_ls, g_ls = sess.run([loss_d, loss_g], feed_dict={X: batch, noise: n, is_training: True}) loss['d'].append(d_ls)
    loss['g'].append(g_ls)
    
    sess.run(optimizer_d, feed_dict={X: batch, noise: n, is_training: True})
    sess.run(optimizer_g, feed_dict={X: batch, noise: n, is_training: True})
    sess.run(optimizer_g, feed_dict={X: batch, noise: n, is_training: True})
        
    if i % 500 == 0:
        print(i, d_ls, g_ls)
        gen_imgs = sess.run(g, feed_dict={noise: z_samples, is_training: False})
        gen_imgs = (gen_imgs + 1) / 2
        imgs = [img[:, :, :] for img in gen_imgs]
        gen_imgs = montage(imgs)
        plt.axis('off')
        plt.imshow(gen_imgs)
        imsave(os.path.join(OUTPUT_DIR, 'sample_%d.jpg' % i), gen_imgs)
        plt.show()
        samples.append(gen_imgs)

plt.plot(loss['d'], label='Discriminator')
plt.plot(loss['g'], label='Generator')
plt.legend(loc='upper right')
plt.savefig(os.path.join(OUTPUT_DIR, 'Loss.png'))
plt.show()
mimsave(os.path.join(OUTPUT_DIR, 'samples.gif'), samples, fps=10)
Copy the code

The LFW results are as follows

CelebA face generation results are as follows

Save the model for later use

saver = tf.train.Saver()
saver.save(sess, os.path.join(OUTPUT_DIR, 'dcgan_' + dataset), global_step=60000)
Copy the code

Use the model to generate face images on a single machine

# -*- coding: utf-8 -*-

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import os

batch_size = 100
z_dim = 100
dataset = 'lfw_new_imgs'
# dataset = 'celeba'

def montage(images):    
    if isinstance(images, list):
        images = np.array(images)
    img_h = images.shape[1]
    img_w = images.shape[2]
    n_plots = int(np.ceil(np.sqrt(images.shape[0])))
    iflen(images.shape) == 4 and images.shape[3] == 3: M = np.ones((images.shape[1] * n_plots + n_plots + 1, images.shape[2] * n_plots + n_plots + 1, 3)) * 0.5eliflen(images.shape) == 4 and images.shape[3] == 1: M = np.ones((images.shape[1] * n_plots + n_plots + 1, images.shape[2] * n_plots + n_plots + 1, 1)) * 0.5eliflen(images.shape) == 3: M = np.ones((images.shape[1] * n_plots + n_plots + 1, images.shape[2] * n_plots + n_plots + 1)) * 0.5else:
        raise ValueError('Could not parse image shape of {}'.format(images.shape))
    for i in range(n_plots):
        for j in range(n_plots):
            this_filter = i * n_plots + j
            if this_filter < images.shape[0]:
                this_img = images[this_filter]
                m[1 + i + i * img_h:1 + i + (i + 1) * img_h,
                  1 + j + j * img_w:1 + j + (j + 1) * img_w] = this_img
    return m

sess = tf.Session()
sess.run(tf.global_variables_initializer())

saver = tf.train.import_meta_graph(os.path.join('samples_' + dataset, 'dcgan_' + dataset + '-60000.meta'))
saver.restore(sess, tf.train.latest_checkpoint('samples_' + dataset))
graph = tf.get_default_graph()
g = graph.get_tensor_by_name('generator/g/Tanh:0')
noise = graph.get_tensor_by_name('noise:0')
is_training = graph.get_tensor_by_name('is_training:0') n = Np.random. Uniform (-1.0, 1.0, [batch_size, z_DIM]).astype(nP.float32) gen_imgs = sess.run(g, feed_dict={noise: n, is_training: False}) gen_imgs = (gen_imgs + 1) / 2 imgs = [img[:, :, :]for img in gen_imgs]
gen_imgs = montage(imgs)
gen_imgs = np.clip(gen_imgs, 0, 1)
plt.figure(figsize=(8, 8))
plt.axis('off')
plt.imshow(gen_imgs)
plt.show()
Copy the code

reference

DCGAN-tensorflow:github.com/carpedm20/D…
LFW：vis-www.cs.umass.edu/lfw/
CelebA:mmlab.ie.cuhk.edu.hk/projects/Ce…

Video lecture course

Deep and interesting (1)

Deep interesting | 08 DCGAN face image generated

Introduction to the

data

implementation

reference

Video lecture course

Related Posts

Will supercomputers, long dismissed as impractical, change in the era of deep learning?

Kaiyuan Big Data Weekly – Issue 29

Collaborative Filtering