无中生有之DCGAN， CGAN， ACGAN

上面一小节中讲了GAN网络，这一节介绍他的兄弟姐妹们

1.DCGAN

DCGAN其实和GAN差不多，只是在网络的部分引入了卷积操作，其他的结构都是一样的（一个生成器，一个辨别器）。

from __future__ import print_function, division

import tensorflow as tf
from tensorflow.keras.datasets import mnist
from tensorflow.keras.layers import Input, Dense, Reshape, Flatten, Dropout, LeakyReLU, UpSampling2D, Conv2D
from tensorflow.keras.layers import BatchNormalization, Activation, ZeroPadding2D, GlobalAveragePooling2D
#from keras.layers.advanced_activations import LeakyReLU
#from keras.layers.convolutional import UpSampling2D, Conv2D
from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.optimizers import Adam

import matplotlib.pyplot as plt

import sys
import os
import numpy as np

#GAN 的生成器和辨别器网络为卷积结构
class DCGAN():
    def __init__(self):
        # 输入shape
        self.img_rows = 28
        self.img_cols = 28
        self.channels = 1
        self.img_shape = (self.img_rows, self.img_cols, self.channels)
        # 分十类
        self.num_classes = 10
        self.latent_dim = 100
        # adam优化器
        optimizer = Adam(0.0002, 0.5)
        # 判别模型
        self.discriminator = self.build_discriminator()
        self.discriminator.compile(loss=['binary_crossentropy'],
            optimizer=optimizer,
            metrics=['accuracy'])
        # 生成模型
        self.generator = self.build_generator()

        # conbine是生成模型和判别模型的结合
        # 判别模型的trainable为False
        # 用于训练生成模型
        z = Input(shape=(self.latent_dim,))  #噪声
        img = self.generator(z)

        self.discriminator.trainable = False

        valid = self.discriminator(img)

        self.combined = Model(z, valid)
        self.combined.compile(loss='binary_crossentropy', optimizer=optimizer)

    def build_generator(self):

        model = Sequential()
        # 先全连接到64*7*7的维度上
        model.add(Dense(32 * 7 * 7, activation="relu", input_dim=self.latent_dim))
        # reshape成特征层的样式
        model.add(Reshape((7, 7, 32)))

        # 7, 7, 64
        model.add(Conv2D(64, kernel_size=3, padding="same"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Activation("relu"))
        # 上采样
        # 7, 7, 64 -> 14, 14, 64
        model.add(UpSampling2D())
        model.add(Conv2D(128, kernel_size=3, padding="same"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Activation("relu"))
        # 上采样
        # 14, 14, 128 -> 28, 28, 64
        model.add(UpSampling2D())
        model.add(Conv2D(64, kernel_size=3, padding="same"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Activation("relu"))

        # 上采样
        # 28, 28, 64 -> 28, 28, 1
        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()
        # 28, 28, 1 -> 14, 14, 32
        model.add(Conv2D(32, kernel_size=3, strides=2, input_shape=self.img_shape, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))
        # 14, 14, 32 -> 7, 7, 64
        model.add(Conv2D(64, kernel_size=3, strides=2, padding="same"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(LeakyReLU(alpha=0.2))
        # 7, 7, 64 -> 4, 4, 128
        model.add(ZeroPadding2D(((0,1),(0,1))))
        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(GlobalAveragePooling2D())
        # 全连接
        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):
        # 载入数据
        (X_train, _), (_, _) = mnist.load_data()

        # 归一化
        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):

            # --------------------- #
            #  训练判别模型
            # --------------------- #
            idx = np.random.randint(0, X_train.shape[0], batch_size)
            imgs = X_train[idx]

            noise = np.random.normal(0, 1, (batch_size, self.latent_dim))
            gen_imgs = self.generator.predict(noise)

            # 训练并计算loss
            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)

            # ---------------------
            #  训练生成模型
            # ---------------------
            g_loss = self.combined.train_on_batch(noise, valid)

            print ("%d [D loss: %f, acc.: %.2f%%] [G loss: %f]" % (epoch, d_loss[0], 100*d_loss[1], g_loss))

            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)
        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__':
    if not os.path.exists("./images"):
        os.makedirs("./images")
    dcgan = DCGAN()
    dcgan.train(epochs=20000, batch_size=256, save_interval=50)

2. CGAN

CGAN就是在输入的时候加了限制条件，既要判断生成图片的真假，又要判断生成图片是否是否符合限制条件。

1、随机选取batch_size个真实的图片和它的标签。
2、随机生成batch_size个N维向量和其对应的标签label，利用Embedding层进行组合，传入到Generator中生成batch_size个虚假图片。
3、Discriminator的loss函数由两部分组成，一部分是真伪的判断结果与真实情况的对比，一部分是图片所属标签的判断结果。
4、Generator的loss函数也由两部分组成，一部分是生成的图片是否被Discriminator判断为1，另一部分是生成的图片是否被分成了正确的类

from __future__ import print_function, division

from keras.datasets import mnist
from keras.layers import Input, Dense, Reshape, Flatten, Dropout, multiply, LeakyReLU, UpSampling2D, Conv2D
from keras.layers import BatchNormalization, Activation, Embedding, ZeroPadding2D
from keras.models import Sequential, Model
from keras.optimizers import Adam

import matplotlib.pyplot as plt
import os
import numpy as np

class CGAN():
    def __init__(self):
        # 输入shape
        self.img_rows = 28
        self.img_cols = 28
        self.channels = 1
        self.img_shape = (self.img_rows, self.img_cols, self.channels)
        # 分十类
        self.num_classes = 10
        self.latent_dim = 100
        # adam优化器
        optimizer = Adam(0.0002, 0.5)
        # 判别模型  两个loss ：一个辨别真伪， 一个判别类别
        losses = ['binary_crossentropy', 'sparse_categorical_crossentropy']
        self.discriminator = self.build_discriminator()
        self.discriminator.compile(loss=losses,
            optimizer=optimizer,
            metrics=['accuracy'])

        # 生成模型
        self.generator = self.build_generator()

        # conbine是生成模型和判别模型的结合
        # 判别模型的trainable为False
        # 用于训练生成模型
        noise = Input(shape=(self.latent_dim,))   
        label = Input(shape=(1,))
        img = self.generator([noise, label])   #Model([noise, label], img)
        self.discriminator.trainable = False
        valid, target_label = self.discriminator(img)  #Model(img, [validity, label])

        #输入是noise 和label 输出是真伪和标签
        self.combined = Model([noise, label], [valid, target_label])
        self.combined.compile(loss=losses,
            optimizer=optimizer)

    #生成器
    def build_generator(self):
        model = Sequential()

        model.add(Dense(256, input_dim=self.latent_dim))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))

        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))

        model.add(Dense(1024))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))

        model.add(Dense(np.prod(self.img_shape), activation='tanh'))
        model.add(Reshape(self.img_shape))

        # 输入一个数字，将其转换为固定尺寸的稠密向量
        # 输出维度是self.latent_dim
        label = Input(shape=(1,), dtype='int32')
        label_embedding = Flatten()(Embedding(self.num_classes, self.latent_dim)(label))

        # 将正态分布和索引对应的稠密向量相乘
        noise = Input(shape=(self.latent_dim,))
        model_input = multiply([noise, label_embedding])
        img = model(model_input)

        return Model([noise, label], img)

    def build_discriminator(self):

        model = Sequential()
        model.add(Flatten(input_shape=self.img_shape))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.4))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.4))

        label = Input(shape=(1,), dtype='int32')
        img = Input(shape=self.img_shape)

        features = model(img)
        # 一个是真伪，一个是类别向量
        validity = Dense(1, activation="sigmoid")(features)
        label = Dense(self.num_classes, activation="softmax")(features)

        return Model(img, [validity, label])
        
    def train(self, epochs, batch_size=128, sample_interval=50):

        # 载入数据库
        (X_train, y_train), (_,  _) = mnist.load_data()

        # 归一化
        X_train = (X_train.astype(np.float32) - 127.5) / 127.5
        X_train = np.expand_dims(X_train, axis=3)
        y_train = y_train.reshape(-1, 1)

        #判断真假
        valid = np.ones((batch_size, 1))  
        fake = np.zeros((batch_size, 1))

        for epoch in range(epochs):

            # --------------------- #
            #  训练鉴别模型
            # --------------------- #
            idx = np.random.randint(0, X_train.shape[0], batch_size)
            imgs, labels = X_train[idx], y_train[idx]

            # ---------------------- # 
            #   生成正态分布的输入
            # ---------------------- #
            noise = np.random.normal(0, 1, (batch_size, self.latent_dim))  #噪声
            sampled_labels = np.random.randint(0, 10, (batch_size, 1)) #标签
            gen_imgs = self.generator.predict([noise, sampled_labels])  #生成假图片

            d_loss_real = self.discriminator.train_on_batch(imgs, [valid, labels])   #真图片的真假和类别的loss
            d_loss_fake = self.discriminator.train_on_batch(gen_imgs, [fake, sampled_labels])  #假图片的真假和类别的loss
            d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)

            # --------------------- #
            #  训练生成模型
            # --------------------- #
            g_loss = self.combined.train_on_batch([noise, sampled_labels], [valid, sampled_labels])  #输入是噪声和标签，最后判断图片是否为真，和label是否对应

            print ("%d [D loss: %f, acc.: %.2f%%, op_acc: %.2f%%] [G loss: %f]" % (epoch, d_loss[0], 100*d_loss[3], 100*d_loss[4], g_loss[0]))

            if epoch % sample_interval == 0:
                self.sample_images(epoch)

    def sample_images(self, epoch):
        r, c = 2, 5
        noise = np.random.normal(0, 1, (r * c, 100))
        sampled_labels = np.arange(0, 10).reshape(-1, 1)

        gen_imgs = self.generator.predict([noise, sampled_labels])
        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].set_title("Digit: %d" % sampled_labels[cnt])
                axs[i,j].axis('off')
                cnt += 1
        fig.savefig("images/%d.png" % epoch)
        plt.close()


if __name__ == '__main__':
    if not os.path.exists("./images"):
        os.makedirs("./images")
    cgan = CGAN()
    cgan.train(epochs=20000, batch_size=256, sample_interval=200)

3. ACGAN

ACGAN 就是DCGAN + CGAN ， 结构都是用的卷积神经网络，然后生成器和鉴别器都加入了附加条件（类别信息）

from __future__ import print_function, division
import tensorflow as tf
from keras.datasets import mnist
from keras.backend.tensorflow_backend import set_session
from keras.layers import Input, Dense, Reshape, Flatten, Dropout, multiply
from keras.layers import BatchNormalization, Activation, Embedding, ZeroPadding2D, GlobalAveragePooling2D
from keras.layers.advanced_activations import LeakyReLU
from keras.layers.convolutional import UpSampling2D, Conv2D
from keras.models import Sequential, Model
from keras.optimizers import Adam

import matplotlib.pyplot as plt
import os
import numpy as np

class ACGAN():
    def __init__(self):
        # 输入shape
        self.img_rows = 28
        self.img_cols = 28
        self.channels = 1
        self.img_shape = (self.img_rows, self.img_cols, self.channels)
        # 分十类
        self.num_classes = 10
        self.latent_dim = 100
        # adam优化器
        optimizer = Adam(0.0002, 0.5)
        # 判别模型
        losses = ['binary_crossentropy', 'sparse_categorical_crossentropy']
        self.discriminator = self.build_discriminator()
        self.discriminator.compile(loss=losses,
            optimizer=optimizer,
            metrics=['accuracy'])

        # 生成模型
        self.generator = self.build_generator()

        # conbine是生成模型和判别模型的结合
        # 判别模型的trainable为False
        # 用于训练生成模型
        noise = Input(shape=(self.latent_dim,))
        label = Input(shape=(1,))
        img = self.generator([noise, label])

        self.discriminator.trainable = False

        valid, target_label = self.discriminator(img)

        self.combined = Model([noise, label], [valid, target_label])
        self.combined.compile(loss=losses,
            optimizer=optimizer)

    def build_generator(self):

        model = Sequential()

        # 先全连接到64*7*7的维度上
        model.add(Dense(32 * 7 * 7, activation="relu", input_dim=self.latent_dim))
        # reshape成特征层的样式
        model.add(Reshape((7, 7, 32)))

        # 7, 7, 64
        model.add(Conv2D(64, kernel_size=3, padding="same"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Activation("relu"))
        # 上采样
        # 7, 7, 64 -> 14, 14, 64
        model.add(UpSampling2D())
        model.add(Conv2D(128, kernel_size=3, padding="same"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Activation("relu"))
        # 上采样
        # 14, 14, 128 -> 28, 28, 64
        model.add(UpSampling2D())
        model.add(Conv2D(64, kernel_size=3, padding="same"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Activation("relu"))

        # 上采样
        # 28, 28, 64 -> 28, 28, 1
        model.add(Conv2D(self.channels, kernel_size=3, padding="same"))
        model.add(Activation("tanh"))


        model.summary()

        noise = Input(shape=(self.latent_dim,))
        label = Input(shape=(1,), dtype='int32')
        label_embedding = Flatten()(Embedding(self.num_classes, self.latent_dim)(label))

        model_input = multiply([noise, label_embedding])
        img = model(model_input)

        return Model([noise, label], img)

    def build_discriminator(self):

        model = Sequential()
        # 28,28,1 -> 14,14,16
        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))
        # 14,14,16 -> 8,8,32
        model.add(Conv2D(32, kernel_size=3, strides=2, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(BatchNormalization(momentum=0.8))
        # 8,8,32 -> 4,4,64
        model.add(ZeroPadding2D(padding=((0,1),(0,1))))
        model.add(Conv2D(64, kernel_size=3, strides=2, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(BatchNormalization(momentum=0.8))
        # 4,4,64 -> 4,4,128
        model.add(Conv2D(128, kernel_size=3, strides=1, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(GlobalAveragePooling2D())

        img = Input(shape=self.img_shape)

        features = model(img)

        validity = Dense(1, activation="sigmoid")(features)
        label = Dense(self.num_classes, activation="softmax")(features)

        return Model(img, [validity, label])

    def train(self, epochs, batch_size=128, sample_interval=50):

        # 载入数据库
        (X_train, y_train), (_,  _) = mnist.load_data()

        # 归一化
        X_train = (X_train.astype(np.float32) - 127.5) / 127.5
        X_train = np.expand_dims(X_train, axis=3)
        y_train = y_train.reshape(-1, 1)

        valid = np.ones((batch_size, 1))
        fake = np.zeros((batch_size, 1))

        for epoch in range(epochs):

            # --------------------- #
            #  训练鉴别模型
            # --------------------- #
            idx = np.random.randint(0, X_train.shape[0], batch_size)
            imgs, labels = X_train[idx], y_train[idx]

            # ---------------------- # 
            #   生成正态分布的输入
            # ---------------------- #
            noise = np.random.normal(0, 1, (batch_size, self.latent_dim))
            sampled_labels = np.random.randint(0, 10, (batch_size, 1))
            gen_imgs = self.generator.predict([noise, sampled_labels])

            d_loss_real = self.discriminator.train_on_batch(imgs, [valid, labels])
            d_loss_fake = self.discriminator.train_on_batch(gen_imgs, [fake, sampled_labels])
            d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)

            # --------------------- #
            #  训练生成模型
            # --------------------- #
            g_loss = self.combined.train_on_batch([noise, sampled_labels], [valid, sampled_labels])

            print ("%d [D loss: %f, acc.: %.2f%%, op_acc: %.2f%%] [G loss: %f]" % (epoch, d_loss[0], 100*d_loss[3], 100*d_loss[4], g_loss[0]))

            if epoch % sample_interval == 0:
                self.sample_images(epoch)


    def sample_images(self, epoch):
        r, c = 2, 5
        noise = np.random.normal(0, 1, (r * c, 100))
        sampled_labels = np.arange(0, 10).reshape(-1, 1)

        gen_imgs = self.generator.predict([noise, sampled_labels])
        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].set_title("Digit: %d" % sampled_labels[cnt])
                axs[i,j].axis('off')
                cnt += 1
        fig.savefig("images/%d.png" % epoch)
        plt.close()
        
    def save_model(self):

        def save(model, model_name):
            model_path = "saved_model/%s.json" % model_name
            weights_path = "saved_model/%s_weights.hdf5" % model_name
            options = {"file_arch": model_path,
                        "file_weight": weights_path}
            json_string = model.to_json()
            open(options['file_arch'], 'w').write(json_string)
            model.save_weights(options['file_weight'])

        save(self.generator, "generator")
        save(self.discriminator, "discriminator")

if __name__ == '__main__':
    if not os.path.exists("./images"):
        os.makedirs("./images")
    acgan = ACGAN()
    acgan.train(epochs=20000, batch_size=256, sample_interval=200)