keras之GAN and wavenet

GAN用于学习怎么生成仿真数据（NIPS 2016 Tutorial: Generative Adversarial Networks, by I.Goodfellow, 2016）

WAVENET是一个深度GAN，用于让电脑生成人声和乐器声。

1.什么是GAN

GAN 主要包括了两个部分，即生成器 generator 与判别器 discriminator。生成器主要用来学习真实图像分布从而让自身生成的图像更加真实，以骗过判别器。判别器则需要对接收的图片进行真假判别。在整个过程中，生成器努力地让生成的图像更加真实，而判别器则努力地去识别出图像的真假，这个过程相当于一个二人博弈，随着时间的推移，生成器和判别器在不断地进行对抗，最终两个网络达到了一个动态均衡：生成器生成的图像接近于真实图像分布，而判别器识别不出真假图像，对于给定图像的预测为真的概率基本接近 0.5（相当于随机猜测类别）。

更多可参照：https://www.leiphone.com/news/201707/1JEkcUZI1leAFq5L.html

2.GAN应用

StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks, by Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaolei Huang, Xiaogang Wang, and Dimitris Metaxas(the code is available online at: https://github.com/hanzhanggit/StackGAN )

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, by A. Radford, L. Metz, and S. Chintala, arXiv: 1511.06434, 2015) used for the generator and the discriminator networks

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks，by A.Radford, L. Metz, and S. Chintala, arXiv

3.深度卷及GAN（DCGAN）

论文来源：Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, by A. Radford, L. Metz, and S. Chintala, arXiv: 1511.06434,2015

https://blog.csdn.net/stdcoutzyx/article/details/53872121

from keras.layers import Dense,BatchNormalization,UpSampling2D
from keras.layers import Conv2D,Activation,Reshape
from keras.models import Sequential

def generator_model():
    model=Sequential()
    model.add(Dense(input_dim=100,output_dim=1024,activation='tanh'))
    model.add(Dense(128*7*7))
    model.add(BatchNormalization())
    model.add(Activation('tanh'))
    model.add(Reshape((128,7,7),input_shape=(128*7*7)))
    model.add(UpSampling2D(size=(2,2)))
    model.add(Conv2D(64,5,5,padding='SAME',activation='tanh'))
    model.add(UpSampling2D(size=(2,2)))
    model.add(Conv2D(1,5,5,padding='SAME',activation='tanh'))
    return model

def	discriminator_model():
    model=Sequential()
    model.add(Convolution2D(64,5,5,border_mode='same',input_shape=(1,28,28)))
    model.add(Activation('tanh'))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(Conv2D(128,5,5))
    model.add(Activation('tanh'))
    model.add(MaxPooling2D(pool_size=(2,	2)))
    model.add(Flatten())
    model.add(Dense(1024))
    model.add(Activation('tanh'))
    model.add(Dense(1))
    model.add(Activation('sigmoid'))
    return model

https://github.com/soumith/ganhacks