[生成对抗网络GAN入门指南](8)SGAN:Semi-Supervised Learning with Generative Adversarial Networks

17 篇文章 11 订阅
17 篇文章 11 订阅

本篇blog的内容基于原始论文SGAN:Semi-Supervised Learning with Generative Adversarial Networks和《生成对抗网络入门指南》第六章。(论文比较短只有3页,其中还包含一页citation)


为什么研究SGAN?

  • 有大量的数据是不带标签的,带标签的数据只占一小部分;

  • 在DCGAN的研究中我们看到使用生成模型特征抽取后形成的判别器可以达到分类的效果。由判别器D学习到的特征可以提升分类器C的效果,两者相辅相成;

  • 现有的训练方式无法同时训练分类器C和生成器G;

  • 提升判别器后,生成器G的效果也会变好;

三者交替会趋向于一个理想的平衡点。

 

一、SGAN

Semi-Supervised Learning with Generative Adversarial Networks

  • 传统的GAN在判别器网络的输出端会使用二分类模式,代表真和假。

  • 在SGAN中,就是把这个二分类(sigmoid)转化为多分类(softmax),类型数量为N+1,指代N个标签的数据和“一个假数据”,表示为 [C_1,C_2.C_n,\ Fake]

 

二、伪代码

                                                         SGAN伪代码


输入:I:总迭代次数

       for\ n=1,\cdots,I \ do

              从生成器前置随机分布 p_g(z) 取出 m 个随机样本 z^{(1)},\cdots ,z^{(m)}

              从真实数据分布 p_{data}(x)取出 m 个真实样本 (x^{(1)},y^{(1)}),\cdots,(x^{(m)},y^{(m)}) ;

              最小化 NLL,更新 D/C 的参数;

              从生成器前置随机分布 p_g(z) 取出 m 个随机样本 z^{(1)},\cdots ,z^{(m)}

              最大化 NLL ,更新 G 的参数;

       end \ for


跟之前的cGAN对比,差别在于:

  • 对于生成器的输入端我们没有将标签信息作为输入,所以判别器产生的生成数据是随机分布的,不受网络输入的控制。

  • 对于判别器的输出而言cGAN仅仅是一个真或者假的二分类,而SGAN则是一个分类器与判别器的结合体。

 

三、实验代码

以MNIST做实验

1. 导入相关包

from __future__ import print_function, division

from keras.datasets import mnist
from keras.layers import Input, Dense, Reshape, Flatten, Dropout, multiply, GaussianNoise
from keras.layers import BatchNormalization, Activation, Embedding, 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 Adam
from keras import losses
from keras.utils import to_categorical
import keras.backend as K

import matplotlib.pyplot as plt

import numpy as np

2. 初始化超参数

class SGAN():
    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.num_classes = 10
        self.latent_dim = 100

        optimizer = Adam(0.0002, 0.5)

3.声明生成器和分类器,并编译

        # Build and compile the discriminator
        self.discriminator = self.build_discriminator()
        self.discriminator.compile(loss=['binary_crossentropy', 'categorical_crossentropy'],
            loss_weights=[0.5, 0.5],
            optimizer=optimizer,
            metrics=['accuracy'])

        # Build the generator
        self.generator = self.build_generator()

        # The generator takes noise as input and generates imgs
        noise = Input(shape=(100,))
        img = self.generator(noise)

        # For the combined model we will only train the generator
        self.discriminator.trainable = False

        # The valid takes generated images as input and determines valid
        valid, _ = self.discriminator(img)

        # The combined model  (stacked generator and discriminator)
        # Trains generator to fool discriminator
        self.combined = Model(noise , valid)
        self.combined.compile(loss=['binary_crossentropy'],
            optimizer=optimizer)

4. 构造生成器和分类器

这里的分类器在最后一步使用softmax,并且label作为条件输入。

        features = model(img)
        valid = Dense(1, activation="sigmoid")(features)
        label = Dense(self.num_classes+1, activation="softmax")(features)

        return Model(img, [valid, label])

    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(BatchNormalization(momentum=0.8))
        model.add(UpSampling2D())
        model.add(Conv2D(128, kernel_size=3, padding="same"))
        model.add(Activation("relu"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(UpSampling2D())
        model.add(Conv2D(64, kernel_size=3, padding="same"))
        model.add(Activation("relu"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Conv2D(1, 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(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Conv2D(128, kernel_size=3, strides=2, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Conv2D(256, kernel_size=3, strides=1, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(Flatten())

        model.summary()

        img = Input(shape=self.img_shape)

        features = model(img)
        valid = Dense(1, activation="sigmoid")(features)
        label = Dense(self.num_classes+1, activation="softmax")(features)

        return Model(img, [valid, label])

 

5. 训练

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

        # Load the dataset
        (X_train, y_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)
        y_train = y_train.reshape(-1, 1)

        # Class weights:
        # To balance the difference in occurences of digit class labels.
        # 50% of labels that the discriminator trains on are 'fake'.
        # Weight = 1 / frequency
        cw1 = {0: 1, 1: 1}
        cw2 = {i: self.num_classes / 64 for i in range(self.num_classes)}
        cw2[self.num_classes] = 1 / 64

        # 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 batch 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)

            # One-hot encoding of labels
            labels = to_categorical(y_train[idx], num_classes=self.num_classes+1)
            fake_labels = to_categorical(np.full((batch_size, 1), self.num_classes), num_classes=self.num_classes+1)

            # Train the discriminator
            d_loss_real = self.discriminator.train_on_batch(imgs, [valid, labels], class_weight=[cw1, cw2])
            d_loss_fake = self.discriminator.train_on_batch(gen_imgs, [fake, fake_labels], class_weight=[cw1, cw2])
            d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)


            # ---------------------
            #  Train Generator
            # ---------------------

            g_loss = self.combined.train_on_batch(noise, valid, class_weight=[cw1, cw2])

            # Plot the progress
            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))

            # If at save interval => save generated image samples
            if epoch % sample_interval == 0:
                self.sample_images(epoch)

 

6. 可视化 并保存model

    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 + 1

        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()

    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, "mnist_sgan_generator")
        save(self.discriminator, "mnist_sgan_discriminator")
        save(self.combined, "mnist_sgan_adversarial")


if __name__ == '__main__':
    sgan = SGAN()
    sgan.train(epochs=20000, batch_size=32, sample_interval=50)

 

四、实验结果

0 [D loss: 0.579261, acc: 39.06%, op_acc: 7.81%] [G loss: 0.713937]

1000 [D loss: 0.316801, acc: 71.88%, op_acc: 54.69%] [G loss: 1.037289]

2000 [D loss: 0.366537, acc: 59.38%, op_acc: 54.69%] [G loss: 0.987430]

3000 [D loss: 0.328151, acc: 67.19%, op_acc: 57.81%] [G loss: 1.385562]

4000 [D loss: 0.343711, acc: 68.75%, op_acc: 57.81%] [G loss: 1.151738]

5000 [D loss: 0.348945, acc: 65.62%, op_acc: 56.25%] [G loss: 1.219509]

6000 [D loss: 0.318236, acc: 67.19%, op_acc: 54.69%] [G loss: 1.235397]

7000 [D loss: 0.368775, acc: 59.38%, op_acc: 51.56%] [G loss: 1.175400]

8000 [D loss: 0.340480, acc: 67.19%, op_acc: 59.38%] [G loss: 1.065718]

 

完整代码

from __future__ import print_function, division

from keras.datasets import mnist
from keras.layers import Input, Dense, Reshape, Flatten, Dropout, multiply, GaussianNoise
from keras.layers import BatchNormalization, Activation, Embedding, 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 Adam
from keras import losses
from keras.utils import to_categorical
import keras.backend as K

import matplotlib.pyplot as plt

import numpy as np

class SGAN():
    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.num_classes = 10
        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', 'categorical_crossentropy'],
            loss_weights=[0.5, 0.5],
            optimizer=optimizer,
            metrics=['accuracy'])

        # Build the generator
        self.generator = self.build_generator()

        # The generator takes noise as input and generates imgs
        noise = Input(shape=(100,))
        img = self.generator(noise)

        # For the combined model we will only train the generator
        self.discriminator.trainable = False

        # The valid takes generated images as input and determines valid
        valid, _ = self.discriminator(img)

        # The combined model  (stacked generator and discriminator)
        # Trains generator to fool discriminator
        self.combined = Model(noise , 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(BatchNormalization(momentum=0.8))
        model.add(UpSampling2D())
        model.add(Conv2D(128, kernel_size=3, padding="same"))
        model.add(Activation("relu"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(UpSampling2D())
        model.add(Conv2D(64, kernel_size=3, padding="same"))
        model.add(Activation("relu"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Conv2D(1, 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(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Conv2D(128, kernel_size=3, strides=2, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Conv2D(256, kernel_size=3, strides=1, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(Flatten())

        model.summary()

        img = Input(shape=self.img_shape)

        features = model(img)
        valid = Dense(1, activation="sigmoid")(features)
        label = Dense(self.num_classes+1, activation="softmax")(features)

        return Model(img, [valid, label])

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

        # Load the dataset
        (X_train, y_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)
        y_train = y_train.reshape(-1, 1)

        # Class weights:
        # To balance the difference in occurences of digit class labels.
        # 50% of labels that the discriminator trains on are 'fake'.
        # Weight = 1 / frequency
        cw1 = {0: 1, 1: 1}
        cw2 = {i: self.num_classes / 64 for i in range(self.num_classes)}
        cw2[self.num_classes] = 1 / 64

        # 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 batch 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)

            # One-hot encoding of labels
            labels = to_categorical(y_train[idx], num_classes=self.num_classes+1)
            fake_labels = to_categorical(np.full((batch_size, 1), self.num_classes), num_classes=self.num_classes+1)

            # Train the discriminator
            d_loss_real = self.discriminator.train_on_batch(imgs, [valid, labels], class_weight=[cw1, cw2])
            d_loss_fake = self.discriminator.train_on_batch(gen_imgs, [fake, fake_labels], class_weight=[cw1, cw2])
            d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)


            # ---------------------
            #  Train Generator
            # ---------------------

            g_loss = self.combined.train_on_batch(noise, valid, class_weight=[cw1, cw2])

            # Plot the progress
            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))

            # 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 + 1

        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()

    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, "mnist_sgan_generator")
        save(self.discriminator, "mnist_sgan_discriminator")
        save(self.combined, "mnist_sgan_adversarial")


if __name__ == '__main__':
    sgan = SGAN()
    sgan.train(epochs=20000, batch_size=32, sample_interval=50)

 

  • 6
    点赞
  • 30
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
1.版本:matlab2014/2019a,内含运行结果,不会运行可私信 2.领域:智能优化算法、神经网络预测、信号处理、元胞自动机、图像处理、路径规划、无人机等多种领域的Matlab仿真,更多内容可点击博主头像 3.内容:标题所示,对于介绍可点击主页搜索博客 4.适合人群:本科,硕士等教研学习使用 5.博客介绍:热爱科研的Matlab仿真开发者,修心和技术同步精进,matlab项目合作可si信 ### 团队长期从事下列领域算法的研究和改进: ### 1 智能优化算法及应用 **1.1 改进智能优化算法方面(单目标和多目标)** **1.2 生产调度方面** 1.2.1 装配线调度研究 1.2.2 车间调度研究 1.2.3 生产线平衡研究 1.2.4 水库梯度调度研究 **1.3 路径规划方面** 1.3.1 旅行商问题研究(TSP、TSPTW) 1.3.2 各类车辆路径规划问题研究(vrp、VRPTW、CVRP) 1.3.3 机器人路径规划问题研究 1.3.4 无人机三维路径规划问题研究 1.3.5 多式联运问题研究 1.3.6 无人机结合车辆路径配送 **1.4 三维装箱求解** **1.5 物流选址研究** 1.5.1 背包问题 1.5.2 物流选址 1.5.4 货位优化 ##### 1.6 电力系统优化研究 1.6.1 微电网优化 1.6.2 配电网系统优化 1.6.3 配电网重构 1.6.4 有序充电 1.6.5 储能双层优化调度 1.6.6 储能优化配置 ### 2 神经网络回归预测、时序预测、分类清单 **2.1 bp预测和分类** **2.2 lssvm预测和分类** **2.3 svm预测和分类** **2.4 cnn预测和分类** ##### 2.5 ELM预测和分类 ##### 2.6 KELM预测和分类 **2.7 ELMAN预测和分类** ##### 2.8 LSTM预测和分类 **2.9 RBF预测和分类** ##### 2.10 DBN预测和分类 ##### 2.11 FNN预测 ##### 2.12 DELM预测和分类 ##### 2.13 BIlstm预测和分类 ##### 2.14 宽度学习预测和分类 ##### 2.15 模糊小波神经网络预测和分类 ##### 2.16 GRU预测和分类 ### 3 图像处理算法 **3.1 图像识别** 3.1.1 车牌、交通标志识别(新能源、国内外、复杂环境下车牌) 3.1.2 发票、身份证、银行卡识别 3.1.3 人脸类别和表情识别 3.1.4 打靶识别 3.1.5 字符识别(字母、数字、手写体、汉字、验证码) 3.1.6 病灶识别 3.1.7 花朵、药材、水果蔬菜识别 3.1.8 指纹、手势、虹膜识别 3.1.9 路面状态和裂缝识别 3.1.10 行为识别 3.1.11 万用表和表盘识别 3.1.12 人民币识别 3.1.13 答题卡识别 **3.2 图像分割** **3.3 图像检测** 3.3.1 显著性检测 3.3.2 缺陷检测 3.3.3 疲劳检测 3.3.4 病害检测 3.3.5 火灾检测 3.3.6 行人检测 3.3.7 水果分级 **3.4 图像隐藏** **3.5 图像去噪** **3.6 图像融合** **3.7 图像配准** **3.8 图像增强** **3.9 图像压缩** ##### 3.10 图像重建 ### 4 信号处理算法 **4.1 信号识别** **4.2 信号检测** **4.3 信号嵌入和提取** **4.4 信号去噪** ##### 4.5 故障诊断 ##### 4.6 脑电信号 ##### 4.7 心电信号 ##### 4.8 肌电信号 ### 5 元胞自动机仿真 **5.1 模拟交通流** **5.2 模拟人群疏散** **5.3 模拟病毒扩散** **5.4 模拟晶体生长** ### 6 无线传感器网络 ##### 6.1 无线传感器定位 ##### 6.2 无线传感器覆盖优化 ##### 6.3 室内定位 ##### 6.4 无线传感器通信及优化 ##### 6.5 无人机通信中继优化

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值