简介在人脸数据上训练DCGAN，并生成一些人脸图片
数据使用两个数据集
实现和上节课的代码差不多，根据彩色图片进行适当调整即可
加载库
# -*- coding: utf-8 -*-import tensorflow as tfimport numpy as npimport urllibimport tarfileimport osimport matplotlib.pyplot as plt%matplotlib inlinefrom imageio import imread, imsave, mimsavefrom scipy.misc import imresizeimport glob复制代码下载LFW数据并解压处理，CelebA数据已经准备好
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复制代码设定用于生成人脸的数据集
# dataset = 'lfw_new_imgs' # LFWdataset = 'celeba' # CelebAimages = glob.glob(os.path.join(dataset, '*.*')) print(len(images))复制代码定义一些常量、网络输入、辅助函数
batch_size = 100z_dim = 100WIDTH = 64HEIGHT = 64OUTPUT_DIR = 'samples_' + datasetif 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)复制代码判别器部分
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复制代码生成器部分
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复制代码损失函数
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复制代码优化函数
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)复制代码读取图片的函数
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.复制代码合成图片的函数
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]))) if len(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)) * 0.5 elif len(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)) * 0.5 elif len(images.shape) == 3: m = np.ones( (images.shape[1] * n_plots + n_plots + 1, images.shape[2] * n_plots + n_plots + 1)) * 0.5 else: 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复制代码模型的训练
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 = 0for i in range(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 in images[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)复制代码LFW人脸生成结果如下
![]()
CelebA人脸生成结果如下
![]()
保存模型，便于后续使用
saver = tf.train.Saver()saver.save(sess, os.path.join(OUTPUT_DIR, 'dcgan_' + dataset), global_step=60000)复制代码在单机上使用模型生成人脸图片
# -*- coding: utf-8 -*-import tensorflow as tfimport numpy as npimport matplotlib.pyplot as pltimport osbatch_size = 100z_dim = 100dataset = '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]))) if len(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)) * 0.5 elif len(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)) * 0.5 elif len(images.shape) == 3: m = np.ones( (images.shape[1] * n_plots + n_plots + 1, images.shape[2] * n_plots + n_plots + 1)) * 0.5 else: 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 msess = 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) / 2imgs = [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()复制代码参考
链接：https://juejin.im/post/5ba258816fb9a05d12280271
|
|
收藏
淘帖
踩
