记录一下

上资源：（github），

基于Pytorch的条件对抗生成网络

条件对抗生成网络和生成对抗网络的区别在于，条件对抗网络生成器和鉴别器额外输入了条件信息（以minist为例，就是额外输入了标签），具体流程如下：

我主要研究其中的CGAN部分，所有代码如下：

import argparse
import os
import numpy as np
import math
import matplotlib.pyplot as plt
import torchvision.transforms as transforms
from torchvision.utils import save_image

from torch.utils.data import DataLoader
from torchvision import datasets
from torch.autograd import Variable

import torch.nn as nn
import torch.nn.functional as F
import torch

os.makedirs("images", exist_ok=True)

parser = argparse.ArgumentParser()
parser.add_argument("--n_epochs", type=int, default=200, help="number of epochs of training")
parser.add_argument("--batch_size", type=int, default=64, help="size of the batches")
parser.add_argument("--lr", type=float, default=0.0002, help="adam: learning rate")
parser.add_argument("--b1", type=float, default=0.5, help="adam: decay of first order momentum of gradient")
parser.add_argument("--b2", type=float, default=0.999, help="adam: decay of first order momentum of gradient")
parser.add_argument("--n_cpu", type=int, default=4, help="number of cpu threads to use during batch generation")
parser.add_argument("--latent_dim", type=int, default=100, help="dimensionality of the latent space")
parser.add_argument("--n_classes", type=int, default=10, help="number of classes for dataset")
parser.add_argument("--img_size", type=int, default=32, help="size of each image dimension")
parser.add_argument("--channels", type=int, default=1, help="number of image channels")
parser.add_argument("--sample_interval", type=int, default=400, help="interval between image sampling")
opt = parser.parse_args()
print(opt)

img_shape = (opt.channels, opt.img_size, opt.img_size)

cuda = True if torch.cuda.is_available() else False


class Generator(nn.Module):
    def __init__(self):
        super(Generator, self).__init__()

        self.label_emb = nn.Embedding(opt.n_classes, opt.n_classes)

        def block(in_feat, out_feat, normalize=True):
            layers = [nn.Linear(in_feat, out_feat)]
            if normalize:
                layers.append(nn.BatchNorm1d(out_feat, 0.8))
            layers.append(nn



                          .LeakyReLU(0.2, inplace=True))
            return layers

        self.model = nn.Sequential(
            *block(opt.latent_dim + opt.n_classes, 128, normalize=False),
            *block(128, 256),
            *block(256, 512),
            *block(512, 1024),
            nn.Linear(1024, int(np.prod(img_shape))),
            nn.Tanh()
        )

    def forward(self, noise, labels):
        # Concatenate label embedding and image to produce input
        gen_input = torch.cat((self.label_emb(labels), noise), -1)
        img = self.model(gen_input)
        img = img.view(img.size(0), *img_shape)
        return img


class Discriminator(nn.Module):
    def __init__(self):
        super(Discriminator, self).__init__()

        self.label_embedding = nn.Embedding(opt.n_classes, opt.n_classes)

        self.model = nn.Sequential(
            nn.Linear(opt.n_classes + int(np.prod(img_shape)), 512),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Linear(512, 512),
            nn.Dropout(0.4),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Linear(512, 512),
            nn.Dropout(0.4),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Linear(512, 1),
        )

    def forward(self, img, labels):
        # Concatenate label embedding and image to produce input
        d_in = torch.cat((img.view(img.size(0), -1), self.label_embedding(labels)), -1)
        validity = self.model(d_in)
        return validity


# Loss functions
adversarial_loss = torch.nn.MSELoss()

# Initialize generator and discriminator
generator = Generator()
discriminator = Discriminator()

if cuda:
    generator.cuda()
    discriminator.cuda()
    adversarial_loss.cuda()

# Configure data loader
os.makedirs("../../data/mnist", exist_ok=True)
dataloader = torch.utils.data.DataLoader(
    datasets.MNIST(
        "../../data/mnist",
        train=True,
        download=True,
        transform=transforms.Compose(
            [transforms.Resize(opt.img_size), transforms.ToTensor(), transforms.Normalize([0.5], [0.5])]
        ),
    ),
    batch_size=opt.batch_size,
    shuffle=True,
)

# Optimizers
optimizer_G = torch.optim.Adam(generator.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))
optimizer_D = torch.optim.Adam(discriminator.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))

FloatTensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor
LongTensor = torch.cuda.LongTensor if cuda else torch.LongTensor


def sample_image(n_row, batches_done):
    """Saves a grid of generated digits ranging from 0 to n_classes"""
    # Sample noise
    z = Variable(FloatTensor(np.random.normal(0, 1, (n_row ** 2, opt.latent_dim))))
    # Get labels ranging from 0 to n_classes for n rows
    labels = np.array([num for _ in range(n_row) for num in range(n_row)])
    labels = Variable(LongTensor(labels))
    gen_imgs = generator(z, labels)
    save_image(gen_imgs.data, "images/%d.png" % batches_done, nrow=n_row, normalize=True)


# ----------
#  Training
# ----------

for epoch in range(opt.n_epochs):
    for i, (imgs, labels) in enumerate(dataloader):

        batch_size = imgs.shape[0]

        # Adversarial ground truths
        valid = Variable(FloatTensor(batch_size, 1).fill_(1.0), requires_grad=False)
        fake = Variable(FloatTensor(batch_size, 1).fill_(0.0), requires_grad=False)

        # Configure input
        real_imgs = Variable(imgs.type(FloatTensor))
        labels = Variable(labels.type(LongTensor))

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

        optimizer_G.zero_grad()

        # Sample noise and labels as generator input
        z = Variable(FloatTensor(np.random.normal(0, 1, (batch_size, opt.latent_dim))))
        gen_labels = Variable(LongTensor(np.random.randint(0, opt.n_classes, batch_size)))

        # Generate a batch of images
        gen_imgs = generator(z, gen_labels)

        # Loss measures generator's ability to fool the discriminator
        validity = discriminator(gen_imgs, gen_labels)
        g_loss = adversarial_loss(validity, valid)

        g_loss.backward()
        optimizer_G.step()

        # ---------------------
        #  Train Discriminator
        # ---------------------

        optimizer_D.zero_grad()

        # Loss for real images
        validity_real = discriminator(real_imgs, labels)
        d_real_loss = adversarial_loss(validity_real, valid)

        # Loss for fake images
        validity_fake = discriminator(gen_imgs.detach(), gen_labels)
        d_fake_loss = adversarial_loss(validity_fake, fake)

        # Total discriminator loss
        d_loss = (d_real_loss + d_fake_loss) / 2

        d_loss.backward()
        optimizer_D.step()

        print(
            "[Epoch %d/%d] [Batch %d/%d] [D loss: %f] [G loss: %f]"
            % (epoch, opt.n_epochs, i, len(dataloader), d_loss.item(), g_loss.item())
        )

        batches_done = epoch * len(dataloader) + i
        if batches_done % opt.sample_interval == 0:
            sample_image(n_row=10, batches_done=batches_done)

代码讲解

一、代码：

import argparse
import os
import numpy as np
import math
import matplotlib.pyplot as plt
import torchvision.transforms as transforms
from torchvision.utils import save_image

from torch.utils.data import DataLoader
from torchvision import datasets
from torch.autograd import Variable

import torch.nn as nn
import torch.nn.functional as F
import torch

导入各种包，主要有argparse、os、numpy、torch。其中torch需要安装pytorch框架，没装的小伙伴，去看这篇博文：

安装教程

os.makedirs("images", exist_ok=True)

创建子文件夹，名称就是images,exist_ok取值为Ture时，已存在该文件夹，也不会报错。

parser = argparse.ArgumentParser()
parser.add_argument("--n_epochs", type=int, default=200, help="number of epochs of training")
parser.add_argument("--batch_size", type=int, default=64, help="size of the batches")
parser.add_argument("--lr", type=float, default=0.0002, help="adam: learning rate")
parser.add_argument("--b1", type=float, default=0.5, help="adam: decay of first order momentum of gradient")
parser.add_argument("--b2", type=float, default=0.999, help="adam: decay of first order momentum of gradient")
parser.add_argument("--n_cpu", type=int, default=4, help="number of cpu threads to use during batch generation")
parser.add_argument("--latent_dim", type=int, default=100, help="dimensionality of the latent space")
parser.add_argument("--n_classes", type=int, default=10, help="number of classes for dataset")
parser.add_argument("--img_size", type=int, default=32, help="size of each image dimension")
parser.add_argument("--channels", type=int, default=1, help="number of image channels")
parser.add_argument("--sample_interval", type=int, default=400, help="interval between image sampling")
opt = parser.parse_args()
print(opt)

初始化参数，如rpoch次数，batch_size的大小等，sample_interval表示后续间隔保存CGAN图片的保存间隔。

img_shape = (opt.channels, opt.img_size, opt.img_size)

cuda = True if torch.cuda.is_available() else False

img_shape表示图片的大小，维度

cuda表示是否具备GPU加速的条件。

class Generator(nn.Module):
    def __init__(self):
        super(Generator, self).__init__()

        self.label_emb = nn.Embedding(opt.n_classes, opt.n_classes)

        def block(in_feat, out_feat, normalize=True):
            layers = [nn.Linear(in_feat, out_feat)]
            if normalize:
                layers.append(nn.BatchNorm1d(out_feat, 0.8))
            layers.append(nn



                          .LeakyReLU(0.2, inplace=True))
            return layers

        self.model = nn.Sequential(
            *block(opt.latent_dim + opt.n_classes, 128, normalize=False),
            *block(128, 256),
            *block(256, 512),
            *block(512, 1024),
            nn.Linear(1024, int(np.prod(img_shape))),
            nn.Tanh()
        )

    def forward(self, noise, labels):
        # Concatenate label embedding and image to produce input
        gen_input = torch.cat((self.label_emb(labels), noise), -1)
        img = self.model(gen_input)
        img = img.view(img.size(0), *img_shape)
        return img

创建生成器类

class Discriminator(nn.Module):
    def __init__(self):
        super(Discriminator, self).__init__()

        self.label_embedding = nn.Embedding(opt.n_classes, opt.n_classes)

        self.model = nn.Sequential(
            nn.Linear(opt.n_classes + int(np.prod(img_shape)), 512),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Linear(512, 512),
            nn.Dropout(0.4),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Linear(512, 512),
            nn.Dropout(0.4),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Linear(512, 1),
        )

    def forward(self, img, labels):
        # Concatenate label embedding and image to produce input
        d_in = torch.cat((img.view(img.size(0), -1), self.label_embedding(labels)), -1)
        validity = self.model(d_in)
        return validity

创建鉴别器类

# Loss functions
adversarial_loss = torch.nn.MSELoss()

# Initialize generator and discriminator
generator = Generator()
discriminator = Discriminator()

if cuda:
    generator.cuda()
    discriminator.cuda()
    adversarial_loss.cuda()

adversarial_loss为损失函数，

generator,discriminator分别为生成器和鉴别器，

if cuda表示如果可以进行GPU加速，则在GPU内建立生成器、鉴别器和损失函数，

os.makedirs("../../data/mnist", exist_ok=True)
dataloader = torch.utils.data.DataLoader(
    datasets.MNIST(
        "../../data/mnist",
        train=True,
        download=True,
        transform=transforms.Compose(
            [transforms.Resize(opt.img_size), transforms.ToTensor(), transforms.Normalize([0.5], [0.5])]
        ),
    ),
    batch_size=opt.batch_size,
    shuffle=True,
)

下载数据，并保存

# Optimizers
optimizer_G = torch.optim.Adam(generator.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))
optimizer_D = torch.optim.Adam(discriminator.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))

FloatTensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor
LongTensor = torch.cuda.LongTensor if cuda else torch.LongTensor

优化器初始化，optimizer_G是生成器的优化函数部分，optimizer_D是鉴别器的

def sample_image(n_row, batches_done):
    """Saves a grid of generated digits ranging from 0 to n_classes"""
    # Sample noise
    z = Variable(FloatTensor(np.random.normal(0, 1, (n_row ** 2, opt.latent_dim))))
    # Get labels ranging from 0 to n_classes for n rows
    labels = np.array([num for _ in range(n_row) for num in range(n_row)])
    labels = Variable(LongTensor(labels))
    gen_imgs = generator(z, labels)
    save_image(gen_imgs.data, "images/%d.png" % batches_done, nrow=n_row, normalize=True)

这是一个生成网格图片的函数。

下面开始算法的正文：

        # Adversarial ground truths
        valid = Variable(FloatTensor(batch_size, 1).fill_(1.0), requires_grad=False)
        fake = Variable(FloatTensor(batch_size, 1).fill_(0.0), requires_grad=False)

        # Configure input
        real_imgs = Variable(imgs.type(FloatTensor))
        labels = Variable(labels.type(LongTensor))

初始配置。

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

        optimizer_G.zero_grad()

        # Sample noise and labels as generator input
        z = Variable(FloatTensor(np.random.normal(0, 1, (batch_size, opt.latent_dim))))
        gen_labels = Variable(LongTensor(np.random.randint(0, opt.n_classes, batch_size)))

        # Generate a batch of images
        gen_imgs = generator(z, gen_labels)

        # Loss measures generator's ability to fool the discriminator
        validity = discriminator(gen_imgs, gen_labels)
        g_loss = adversarial_loss(validity, valid)

        g_loss.backward()
        optimizer_G.step()

训练生成器，先进行梯度归零，参考 这篇文章。接着，生成随机噪声z，单个样本的随机噪声为向量，这里的z大小为batch_size乘以单个样本的随机噪声，gen_labels表示随机生成的条件。然后，gen_imgs表示生成器根据随机噪声z和随机条件生成的样本数据，validity表示鉴别器根据随机图片和随机条件计算获得准确率，g_loss表示损失，衡量生成器的损失大小。g_loss.backward()表示反向传播计算，计算梯度，optimizer_G.step()表示计算更新参数（这个个解释可能有争议，具体没深入）。

        # ---------------------
        #  Train Discriminator
        # ---------------------

        optimizer_D.zero_grad()

        # Loss for real images
        validity_real = discriminator(real_imgs, labels)
        d_real_loss = adversarial_loss(validity_real, valid)

        # Loss for fake images
        validity_fake = discriminator(gen_imgs.detach(), gen_labels)
        d_fake_loss = adversarial_loss(validity_fake, fake)

        # Total discriminator loss
        d_loss = (d_real_loss + d_fake_loss) / 2

        d_loss.backward()
        optimizer_D.step()

这部分是训练鉴别器，开始进行鉴别器的梯度置零，计算真实样本的真实率和误差，再计算生成样本的错误率和误差，总的误差取平均，进行反向传播计算，计算梯度，更新鉴别器的参数。

        print(
            "[Epoch %d/%d] [Batch %d/%d] [D loss: %f] [G loss: %f]"
            % (epoch, opt.n_epochs, i, len(dataloader), d_loss.item(), g_loss.item())
        )

打印输出训练的进度，鉴别器的损失和生成器的损失，

        batches_done = epoch * len(dataloader) + i
        if batches_done % opt.sample_interval == 0:
            sample_image(n_row=10, batches_done=batches_done)

输出每隔opt.sample_interval的样本图片。

附上原文的伪代码流程：

 其中，注意到，这个流程是先更新K次鉴别器，再更新1次生成器，我理解的鉴别器训练次数多一点，对图片样本是否是真实样本判断更准确一些，这样生成器生成的图片就会越逼近于真是样本。不过在源码中，k的值为1，即训练一次生成器，训练一次鉴别器。

参考文献：

1、Mirza M, Osindero S. Conditional generative adversarial nets[J]. arXiv preprint arXiv:1411.1784, 2014.

2、Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[J]. Advances in neural information processing systems, 2014, 27.

 

# 生成对抗网络 # pytorch # 深度学习
Logo
华为开发者空间

华为开发者空间，是为全球开发者打造的专属开发空间，汇聚了华为优质开发资源及工具，致力于让每一位开发者拥有一台云主机，基于华为根生态开发、创新。

更多推荐

cover

GaussDB高智能--智能优化器介绍

avatar 华为开发者空间
cover

华为技术专家出品，《华为开发者空间案例指南》带你玩转云上20+场景应用开发

avatar 华为开发者空间
cover

在华为开发者空间，基于鲲鹏服务器快速开发打砖块小游戏

avatar 华为开发者空间