活动地址:CSDN21天学习挑战赛
- 本文为365天深度学习训练营 中的学习记录博客
- 参考文章地址: 深度学习100例-生成对抗网络(GAN)手写数字生成 | 第18天
- 作者:K同学啊
本文将采用GAN模型实现手写数字的生成。
import tensorflow as tf
gpus = tf.config.list_physical_devices("GPU")
if gpus:
tf.config.experimental.set_memory_growth(gpus[0], True) #设置GPU显存用量按需使用
tf.config.set_visible_devices([gpus[0]],"GPU")
# 打印显卡信息,确认GPU可用
print(gpus)
from tensorflow.keras import layers, datasets, Sequential, Model, optimizers
from tensorflow.keras.layers import LeakyReLU, UpSampling2D, Conv2D
import matplotlib.pyplot as plt
import numpy as np
import sys,os,pathlib
img_shape = (28, 28, 1)
latent_dim = 200
生成对抗网络包括生成器、判别器,两个模型通过对抗训练不断学习、进化。
生成器:生成数据(大部分情况下是图像),目的是“骗过”判别器;
判别器:判断这张图片是真实的还是机器生成的,目的是找出生成器生成的“假数据”。
GAN应用领域十分广泛,包括图像合成、风格迁移、照片修复、数据增强等。
●1.生成器(Generator) 接收随机数并返回生成图像。
●2.将生成的数字图像与实际数据集中的数字图像一起送到鉴别器(Discriminator)。
●3.鉴别器(Discriminator) 接收真实和假图像并返回概率,0到1之间的数字,1表示真,0表示假。
def build_generator():
# ======================================= #
# 生成器,输入一串随机数字生成图片
# ======================================= #
model = Sequential([
layers.Dense(256, input_dim=latent_dim),
layers.LeakyReLU(alpha=0.2), # 高级一点的激活函数
layers.BatchNormalization(momentum=0.8), # BN 归一化
layers.Dense(512),
layers.LeakyReLU(alpha=0.2),
layers.BatchNormalization(momentum=0.8),
layers.Dense(1024),
layers.LeakyReLU(alpha=0.2),
layers.BatchNormalization(momentum=0.8),
layers.Dense(np.prod(img_shape), activation='tanh'),
layers.Reshape(img_shape)
])
noise = layers.Input(shape=(latent_dim,))
img = model(noise)
return Model(noise, img)
def build_discriminator():
# ===================================== #
# 鉴别器,对输入的图片进行判别真假
# ===================================== #
model = Sequential([
layers.Flatten(input_shape=img_shape),
layers.Dense(512),
layers.LeakyReLU(alpha=0.2),
layers.Dense(256),
layers.LeakyReLU(alpha=0.2),
layers.Dense(1, activation='sigmoid')
])
img = layers.Input(shape=img_shape)
validity = model(img)
return Model(img, validity)
# 创建判别器
discriminator = build_discriminator()
# 定义优化器
optimizer = tf.keras.optimizers.Adam(1e-4)
discriminator.compile(loss='binary_crossentropy',
optimizer=optimizer,
metrics=['accuracy'])
# 创建生成器
generator = build_generator()
gan_input = layers.Input(shape=(latent_dim,))
img = generator(gan_input)
# 在训练generate的时候不训练discriminator
discriminator.trainable = False
# 对生成的假图片进行预测
validity = discriminator(img)
combined = Model(gan_input, validity)
combined.compile(loss='binary_crossentropy', optimizer=optimizer)
def sample_images(epoch):
"""
保存样例图片
"""
row, col = 4, 4
noise = np.random.normal(0, 1, (row*col, latent_dim))
gen_imgs = generator.predict(noise)
fig, axs = plt.subplots(row, col)
cnt = 0
for i in range(row):
for j in range(col):
axs[i,j].imshow(gen_imgs[cnt, :,:,0], cmap='gray')
axs[i,j].axis('off')
cnt += 1
fig.savefig("images/%05d.png" % epoch)
plt.close()
def train(epochs, batch_size=128, sample_interval=50):
# 加载数据
(train_images,_), (_,_) = tf.keras.datasets.mnist.load_data()
# 将图片标准化到 [-1, 1] 区间内
train_images = (train_images - 127.5) / 127.5
# 数据
train_images = np.expand_dims(train_images, axis=3)
# 创建标签
true = np.ones((batch_size, 1))
fake = np.zeros((batch_size, 1))
# 进行循环训练
for epoch in range(epochs):
# 随机选择 batch_size 张图片
idx = np.random.randint(0, train_images.shape[0], batch_size)
imgs = train_images[idx]
# 生成噪音
noise = np.random.normal(0, 1, (batch_size, latent_dim))
# 生成器通过噪音生成图片,gen_imgs的shape为:(128, 28, 28, 1)
gen_imgs = generator.predict(noise)
# 训练鉴别器
d_loss_true = discriminator.train_on_batch(imgs, true)
d_loss_fake = discriminator.train_on_batch(gen_imgs, fake)
# 返回loss值
d_loss = 0.5 * np.add(d_loss_true, d_loss_fake)
# 训练生成器
noise = np.random.normal(0, 1, (batch_size, latent_dim))
g_loss = combined.train_on_batch(noise, true)
print ("%d [D loss: %f, acc.: %.2f%%] [G loss: %f]" % (epoch, d_loss[0], 100*d_loss[1], g_loss))
# 保存样例图片
if epoch % sample_interval == 0:
sample_images(epoch)
train(epochs=10000, batch_size=256, sample_interval=200)
import imageio
def compose_gif():
# 图片地址
data_dir = "images"
data_dir = pathlib.Path(data_dir)
paths = list(data_dir.glob('*'))
gif_images = []
for path in paths:
print(path)
gif_images.append(imageio.imread(path))
imageio.mimsave("test.gif",gif_images,fps=2)
compose_gif()