1.介绍
DCGAN是继GAN之后比较好的改进,DCGAN中的DC是“DEEP CONVOLUTIONAL”缩写,从标题,我们就可以知道它和原始GAN(GAN 简介与代码实战_天竺街潜水的八角的博客-CSDN博客)的区别在于网络结构。更加详细的介绍可以参见论文:UNSUPERVISED REPRESENTATION LEARNING WITH DEEP CONVOLUTIONAL GENERATIVE ADVERSARIAL NETWORKS
2.模型结构
对于下图的网络结构,我们会发现,噪声Z(维度为100)传入网络之后,经过全连接变成维度16384,接着reshape成4*4*1024(4*4*1024 = 16384)的特征图,以方便传到后面的卷积层。
3.模型特点
DCGAN能改进GAN训练稳定的原因主要有:
1. 在判别器D中将pooling层用convolutions替代,使得在下采样的时候,卷积可以很好的提取到自己想要的。
2. 生成器G和判别器D中几乎每一层都使用batchnorm层,将特征层的输出归一化到一起,加速了训练,提升了训练的稳定性。(生成器的最后一层和判别器的第一层不加batchnorm)
3. 在判别器中使用leakrelu激活函数,而不是RELU,防止梯度稀疏,生成器中仍然采用relu,但是输出层采用tanh。
4.代码实现 keras
class DCGAN():
def __init__(self):
# Input shape
self.img_rows = 28
self.img_cols = 28
self.channels = 1
self.img_shape = (self.img_rows, self.img_cols, self.channels)
self.latent_dim = 100
optimizer = Adam(0.0002, 0.5)
# Build and compile the discriminator
self.discriminator = self.build_discriminator()
self.discriminator.compile(loss='binary_crossentropy',
optimizer=optimizer,
metrics=['accuracy'])
# Build the generator
self.generator = self.build_generator()
# The generator takes noise as input and generates imgs
z = Input(shape=(self.latent_dim,))
img = self.generator(z)
# For the combined model we will only train the generator
self.discriminator.trainable = False
# The discriminator takes generated images as input and determines validity
valid = self.discriminator(img)
# The combined model (stacked generator and discriminator)
# Trains the generator to fool the discriminator
self.combined = Model(z, valid)
self.combined.compile(loss='binary_crossentropy', optimizer=optimizer)
def build_generator(self):
model = Sequential()
model.add(Dense(128 * 7 * 7, activation="relu", input_dim=self.latent_dim))
model.add(Reshape((7, 7, 128)))
model.add(UpSampling2D())
model.add(Conv2D(128, kernel_size=3, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(UpSampling2D())
model.add(Conv2D(64, kernel_size=3, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(Conv2D(self.channels, kernel_size=3, padding="same"))
model.add(Activation("tanh"))
model.summary()
noise = Input(shape=(self.latent_dim,))
img = model(noise)
return Model(noise, img)
def build_discriminator(self):
model = Sequential()
model.add(Conv2D(32, kernel_size=3, strides=2, input_shape=self.img_shape, padding="same"))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.25))
model.add(Conv2D(64, kernel_size=3, strides=2, padding="same"))
model.add(ZeroPadding2D(padding=((0,1),(0,1))))
model.add(BatchNormalization(momentum=0.8))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.25))
model.add(Conv2D(128, kernel_size=3, strides=2, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.25))
model.add(Conv2D(256, kernel_size=3, strides=1, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(1, activation='sigmoid'))
model.summary()
img = Input(shape=self.img_shape)
validity = model(img)
return Model(img, validity)
def train(self, epochs, batch_size=128, save_interval=50):
# Load the dataset
(X_train, _), (_, _) = mnist.load_data()
# Rescale -1 to 1
X_train = X_train / 127.5 - 1.
X_train = np.expand_dims(X_train, axis=3)
# Adversarial ground truths
valid = np.ones((batch_size, 1))
fake = np.zeros((batch_size, 1))
for epoch in range(epochs):
# ---------------------
# Train Discriminator
# ---------------------
# Select a random half of images
idx = np.random.randint(0, X_train.shape[0], batch_size)
imgs = X_train[idx]
# Sample noise and generate a batch of new images
noise = np.random.normal(0, 1, (batch_size, self.latent_dim))
gen_imgs = self.generator.predict(noise)
# Train the discriminator (real classified as ones and generated as zeros)
d_loss_real = self.discriminator.train_on_batch(imgs, valid)
d_loss_fake = self.discriminator.train_on_batch(gen_imgs, fake)
d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)
# ---------------------
# Train Generator
# ---------------------
# Train the generator (wants discriminator to mistake images as real)
g_loss = self.combined.train_on_batch(noise, valid)
# Plot the progress
print ("%d [D loss: %f, acc.: %.2f%%] [G loss: %f]" % (epoch, d_loss[0], 100*d_loss[1], g_loss))
# If at save interval => save generated image samples
if epoch % save_interval == 0:
self.save_imgs(epoch)
def save_imgs(self, epoch):
r, c = 5, 5
noise = np.random.normal(0, 1, (r * c, self.latent_dim))
gen_imgs = self.generator.predict(noise)
# Rescale images 0 - 1
gen_imgs = 0.5 * gen_imgs + 0.5
fig, axs = plt.subplots(r, c)
cnt = 0
for i in range(r):
for j in range(c):
axs[i,j].imshow(gen_imgs[cnt, :,:,0], cmap='gray')
axs[i,j].axis('off')
cnt += 1
fig.savefig("images/mnist_%d.png" % epoch)
plt.close()