原创文章，转载请注明： 转载自慢慢的回味
本文链接地址: WGAN-GP与WGAN的区别
WGAN-GP与WGAN的区别
相比较WGAN，WGAN-GP不再使用clip野蛮的剪裁鉴别网络的梯度值，而是使用梯度惩罚来使梯度更新平滑，即满足1-lipschitz条件，解决了训练梯度消失梯度爆炸的问题。
WGAN视频讲解参考
1 使用随机方式把真实图片和伪造图片混合在一起。
class RandomWeightedAverage(_Merge): """Provides a (random) weighted average between real and generated image samples""" def _merge_function(self, inputs): alpha = K.random_uniform((32, 1, 1, 1)) return (alpha * inputs[0]) + ((1 - alpha) * inputs[1]) |
2 对真实的图片real_img，伪造的图片fake_img和混合的图片interpolated_img创建鉴别网络critic_model进行鉴别。
它们的损失函数分别为wasserstein_loss，wasserstein_loss和partial_gp_loss。
预测结果分别为valid，fake和validity_interpolated。
# Construct weighted average between real and fake images interpolated_img = RandomWeightedAverage()([real_img, fake_img]) # Determine validity of weighted sample validity_interpolated = self.critic(interpolated_img) # Use Python partial to provide loss function with additional # 'averaged_samples' argument partial_gp_loss = partial(self.gradient_penalty_loss, averaged_samples=interpolated_img) partial_gp_loss.__name__ = 'gradient_penalty' # Keras requires function names self.critic_model = Model(inputs=[real_img, z_disc], outputs=[valid, fake, validity_interpolated]) self.critic_model.compile(loss=[self.wasserstein_loss, self.wasserstein_loss, partial_gp_loss], optimizer=optimizer, loss_weights=[1, 1, 10]) |
目标值分别为-1，1和0。dummy其实只是一个占位，因为gradient_penalty_loss并不会使用目标值。
valid = -np.ones((batch_size, 1)) fake = np.ones((batch_size, 1)) dummy = np.zeros((batch_size, 1)) # Dummy gt for gradient penalty |
3 梯度惩罚损失函数gradient_penalty_loss只需要算预测值y_pred
根据梯度gradients计算欧几里德距离gradient_l2_norm，然后把这个距离和1比较，显然越靠近1，损失越小，惩罚越小。即既不让梯度过快的变化，也不要过慢的变化，刚好满足1-lipschitz最好。
def gradient_penalty_loss(self, y_true, y_pred, averaged_samples): """ Computes gradient penalty based on prediction and weighted real / fake samples """ gradients = K.gradients(y_pred, averaged_samples)[0] # compute the euclidean norm by squaring ... gradients_sqr = K.square(gradients) # ... summing over the rows ... gradients_sqr_sum = K.sum(gradients_sqr, axis=np.arange(1, len(gradients_sqr.shape))) # ... and sqrt gradient_l2_norm = K.sqrt(gradients_sqr_sum) # compute lambda * (1 - ||grad||)^2 still for each single sample gradient_penalty = K.square(1 - gradient_l2_norm) # return the mean as loss over all the batch samples return K.mean(gradient_penalty) |
附基于Keras的WGAN-GP测试程序
# Large amount of credit goes to: # https://github.com/keras-team/keras-contrib/blob/master/examples/improved_wgan.py # which I've used as a reference for this implementation from __future__ import print_function, division from keras.datasets import mnist from keras.layers.merge import _Merge from keras.layers import Input, Dense, Reshape, Flatten, Dropout from keras.layers import BatchNormalization, Activation, ZeroPadding2D from keras.layers.advanced_activations import LeakyReLU from keras.layers.convolutional import UpSampling2D, Conv2D from keras.models import Sequential, Model from keras.optimizers import RMSprop from functools import partial import keras.backend as K import matplotlib.pyplot as plt import sys import numpy as np class RandomWeightedAverage(_Merge): """Provides a (random) weighted average between real and generated image samples""" def _merge_function(self, inputs): alpha = K.random_uniform((32, 1, 1, 1)) return (alpha * inputs[0]) + ((1 - alpha) * inputs[1]) class WGANGP(): def __init__(self): 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 # Following parameter and optimizer set as recommended in paper self.n_critic = 5 optimizer = RMSprop(lr=0.00005) # Build the generator and critic self.generator = self.build_generator() self.critic = self.build_critic() #------------------------------- # Construct Computational Graph # for the Critic #------------------------------- # Freeze generator's layers while training critic self.generator.trainable = False # Image input (real sample) real_img = Input(shape=self.img_shape) # Noise input z_disc = Input(shape=(self.latent_dim,)) # Generate image based of noise (fake sample) fake_img = self.generator(z_disc) # Discriminator determines validity of the real and fake images fake = self.critic(fake_img) valid = self.critic(real_img) # Construct weighted average between real and fake images interpolated_img = RandomWeightedAverage()([real_img, fake_img]) # Determine validity of weighted sample validity_interpolated = self.critic(interpolated_img) # Use Python partial to provide loss function with additional # 'averaged_samples' argument partial_gp_loss = partial(self.gradient_penalty_loss, averaged_samples=interpolated_img) partial_gp_loss.__name__ = 'gradient_penalty' # Keras requires function names self.critic_model = Model(inputs=[real_img, z_disc], outputs=[valid, fake, validity_interpolated]) self.critic_model.compile(loss=[self.wasserstein_loss, self.wasserstein_loss, partial_gp_loss], optimizer=optimizer, loss_weights=[1, 1, 10]) #------------------------------- # Construct Computational Graph # for Generator #------------------------------- # For the generator we freeze the critic's layers self.critic.trainable = False self.generator.trainable = True # Sampled noise for input to generator z_gen = Input(shape=(100,)) # Generate images based of noise img = self.generator(z_gen) # Discriminator determines validity valid = self.critic(img) # Defines generator model self.generator_model = Model(z_gen, valid) self.generator_model.compile(loss=self.wasserstein_loss, optimizer=optimizer) def gradient_penalty_loss(self, y_true, y_pred, averaged_samples): """ Computes gradient penalty based on prediction and weighted real / fake samples """ gradients = K.gradients(y_pred, averaged_samples)[0] # compute the euclidean norm by squaring ... gradients_sqr = K.square(gradients) # ... summing over the rows ... gradients_sqr_sum = K.sum(gradients_sqr, axis=np.arange(1, len(gradients_sqr.shape))) # ... and sqrt gradient_l2_norm = K.sqrt(gradients_sqr_sum) # compute lambda * (1 - ||grad||)^2 still for each single sample gradient_penalty = K.square(1 - gradient_l2_norm) # return the mean as loss over all the batch samples return K.mean(gradient_penalty) def wasserstein_loss(self, y_true, y_pred): return K.mean(y_true * y_pred) 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=4, padding="same")) model.add(BatchNormalization(momentum=0.8)) model.add(Activation("relu")) model.add(UpSampling2D()) model.add(Conv2D(64, kernel_size=4, padding="same")) model.add(BatchNormalization(momentum=0.8)) model.add(Activation("relu")) model.add(Conv2D(self.channels, kernel_size=4, padding="same")) model.add(Activation("tanh")) model.summary() noise = Input(shape=(self.latent_dim,)) img = model(noise) return Model(noise, img) def build_critic(self): model = Sequential() model.add(Conv2D(16, 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(32, 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(64, 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(128, 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)) model.summary() img = Input(shape=self.img_shape) validity = model(img) return Model(img, validity) def train(self, epochs, batch_size, sample_interval=50): # Load the dataset (X_train, _), (_, _) = mnist.load_data() # Rescale -1 to 1 X_train = (X_train.astype(np.float32) - 127.5) / 127.5 X_train = np.expand_dims(X_train, axis=3) # Adversarial ground truths valid = -np.ones((batch_size, 1)) fake = np.ones((batch_size, 1)) dummy = np.zeros((batch_size, 1)) # Dummy gt for gradient penalty for epoch in range(epochs): for _ in range(self.n_critic): # --------------------- # Train Discriminator # --------------------- # Select a random batch of images idx = np.random.randint(0, X_train.shape[0], batch_size) imgs = X_train[idx] # Sample generator input noise = np.random.normal(0, 1, (batch_size, self.latent_dim)) # Train the critic d_loss = self.critic_model.train_on_batch([imgs, noise], [valid, fake, dummy]) # --------------------- # Train Generator # --------------------- g_loss = self.generator_model.train_on_batch(noise, valid) # Plot the progress print ("%d [D loss: %f] [G loss: %f]" % (epoch, d_loss[0], g_loss)) # If at save interval => save generated image samples if epoch % sample_interval == 0: self.sample_images(epoch) def sample_images(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() if __name__ == '__main__': wgan = WGANGP() wgan.train(epochs=30000, batch_size=32, sample_interval=100) |
本作品采用知识共享署名 4.0 国际许可协议进行许可。