DCGAN原理

DCGAN（深度卷积对抗生成网络，Deep Convolutional Generative Adversarial Networks）是GAN的直接扩展。不同之处在于，DCGAN会分别在判别器和生成器中使用卷积和转置卷积层。

数据准备与处理

from download import download

url = "https://download.mindspore.cn/dataset/Faces/faces.zip"

path = download(url, "./faces", kind="zip", replace=True)

数据处理

为执行过程定义一些输入：

batch_size = 128          # 批量大小
image_size = 64           # 训练图像空间大小
nc = 3                    # 图像彩色通道数
nz = 100                  # 隐向量的长度
ngf = 64                  # 特征图在生成器中的大小
ndf = 64                  # 特征图在判别器中的大小
num_epochs = 3           # 训练周期数
lr = 0.0002               # 学习率
beta1 = 0.5               # Adam优化器的beta1超参数

数据处理和增强：

import numpy as np
import mindspore.dataset as ds
import mindspore.dataset.vision as vision

def create_dataset_imagenet(dataset_path):
    """数据加载"""
    dataset = ds.ImageFolderDataset(dataset_path,
                                    num_parallel_workers=4,
                                    shuffle=True,
                                    decode=True)

    # 数据增强操作
    transforms = [
        vision.Resize(image_size),
        vision.CenterCrop(image_size),
        vision.HWC2CHW(),
        lambda x: ((x / 255).astype("float32"))
    ]

    # 数据映射操作
    dataset = dataset.project('image')
    dataset = dataset.map(transforms, 'image')

    # 批量操作
    dataset = dataset.batch(batch_size)
    return dataset

dataset = create_dataset_imagenet('./faces')

将数据转换成字典迭代器，并可视化部分训练数据：

import matplotlib.pyplot as plt

def plot_data(data):
    # 可视化部分训练数据
    plt.figure(figsize=(10, 3), dpi=140)
    for i, image in enumerate(data[0][:30], 1):
        plt.subplot(3, 10, i)
        plt.axis("off")
        plt.imshow(image.transpose(1, 2, 0))
    plt.show()

sample_data = next(dataset.create_tuple_iterator(output_numpy=True))
plot_data(sample_data)

构造网络

生成器

该功能是通过一系列 Conv2dTranspose 转置卷积层来完成的，每个层都与 BatchNorm2d 层和 ReLu 激活层配对，输出数据会经过 tanh 函数，使其返回 [-1,1] 的数据范围内。

DCGAN生成结构如下：

代码实现：

import mindspore as ms
from mindspore import nn, ops
from mindspore.common.initializer import Normal

weight_init = Normal(mean=0, sigma=0.02)
gamma_init = Normal(mean=1, sigma=0.02)

class Generator(nn.Cell):
    """DCGAN网络生成器"""

    def __init__(self):
        super(Generator, self).__init__()
        self.generator = nn.SequentialCell(
            nn.Conv2dTranspose(nz, ngf * 8, 4, 1, 'valid', weight_init=weight_init),
            nn.BatchNorm2d(ngf * 8, gamma_init=gamma_init),
            nn.ReLU(),
            nn.Conv2dTranspose(ngf * 8, ngf * 4, 4, 2, 'pad', 1, weight_init=weight_init),
            nn.BatchNorm2d(ngf * 4, gamma_init=gamma_init),
            nn.ReLU(),
            nn.Conv2dTranspose(ngf * 4, ngf * 2, 4, 2, 'pad', 1, weight_init=weight_init),
            nn.BatchNorm2d(ngf * 2, gamma_init=gamma_init),
            nn.ReLU(),
            nn.Conv2dTranspose(ngf * 2, ngf, 4, 2, 'pad', 1, weight_init=weight_init),
            nn.BatchNorm2d(ngf, gamma_init=gamma_init),
            nn.ReLU(),
            nn.Conv2dTranspose(ngf, nc, 4, 2, 'pad', 1, weight_init=weight_init),
            nn.Tanh()
            )

    def construct(self, x):
        return self.generator(x)

generator = Generator()

判别器

使用卷积而不是通过池化来进行下采样是一个好方法，因为它可以让网络学习自己的池化特征。

代码实现如下：

class Discriminator(nn.Cell):
    """DCGAN网络判别器"""

    def __init__(self):
        super(Discriminator, self).__init__()
        self.discriminator = nn.SequentialCell(
            nn.Conv2d(nc, ndf, 4, 2, 'pad', 1, weight_init=weight_init),
            nn.LeakyReLU(0.2),
            nn.Conv2d(ndf, ndf * 2, 4, 2, 'pad', 1, weight_init=weight_init),
            nn.BatchNorm2d(ngf * 2, gamma_init=gamma_init),
            nn.LeakyReLU(0.2),
            nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 'pad', 1, weight_init=weight_init),
            nn.BatchNorm2d(ngf * 4, gamma_init=gamma_init),
            nn.LeakyReLU(0.2),
            nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 'pad', 1, weight_init=weight_init),
            nn.BatchNorm2d(ngf * 8, gamma_init=gamma_init),
            nn.LeakyReLU(0.2),
            nn.Conv2d(ndf * 8, 1, 4, 1, 'valid', weight_init=weight_init),
            )
        self.adv_layer = nn.Sigmoid()

    def construct(self, x):
        out = self.discriminator(x)
        out = out.reshape(out.shape[0], -1)
        return self.adv_layer(out)

discriminator = Discriminator()

模型训练

损失函数

定义交叉熵损失函数BCELoss

# 定义损失函数
adversarial_loss = nn.BCELoss(reduction='mean')

优化器

# 为生成器和判别器设置优化器
optimizer_D = nn.Adam(discriminator.trainable_params(), learning_rate=lr, beta1=beta1)
optimizer_G = nn.Adam(generator.trainable_params(), learning_rate=lr, beta1=beta1)
optimizer_G.update_parameters_name('optim_g.')
optimizer_D.update_parameters_name('optim_d.')

训练模型

训练判别器

训练判别器的目的是最大程度地提高判别图像真伪的概率。通过提高其随机梯度来更新判别器，所以我们要最大化

训练生成器

需要最小化

模型训练正向逻辑：

def generator_forward(real_imgs, valid):
    # 将噪声采样为发生器的输入
    z = ops.standard_normal((real_imgs.shape[0], nz, 1, 1))

    # 生成一批图像
    gen_imgs = generator(z)

    # 损失衡量发生器绕过判别器的能力
    g_loss = adversarial_loss(discriminator(gen_imgs), valid)

    return g_loss, gen_imgs

def discriminator_forward(real_imgs, gen_imgs, valid, fake):
    # 衡量鉴别器从生成的样本中对真实样本进行分类的能力
    real_loss = adversarial_loss(discriminator(real_imgs), valid)
    fake_loss = adversarial_loss(discriminator(gen_imgs), fake)
    d_loss = (real_loss + fake_loss) / 2
    return d_loss

grad_generator_fn = ms.value_and_grad(generator_forward, None,
                                      optimizer_G.parameters,
                                      has_aux=True)
grad_discriminator_fn = ms.value_and_grad(discriminator_forward, None,
                                          optimizer_D.parameters)

@ms.jit
def train_step(imgs):
    valid = ops.ones((imgs.shape[0], 1), mindspore.float32)
    fake = ops.zeros((imgs.shape[0], 1), mindspore.float32)

    (g_loss, gen_imgs), g_grads = grad_generator_fn(imgs, valid)
    optimizer_G(g_grads)
    d_loss, d_grads = grad_discriminator_fn(imgs, gen_imgs, valid, fake)
    optimizer_D(d_grads)

    return g_loss, d_loss, gen_imgs

每50此迭代，手机生成器和判别器的损失

import mindspore

G_losses = []
D_losses = []
image_list = []

total = dataset.get_dataset_size()
for epoch in range(num_epochs):
    generator.set_train()
    discriminator.set_train()
    # 为每轮训练读入数据
    for i, (imgs, ) in enumerate(dataset.create_tuple_iterator()):
        g_loss, d_loss, gen_imgs = train_step(imgs)
        if i % 100 == 0 or i == total - 1:
            # 输出训练记录
            print('[%2d/%d][%3d/%d]   Loss_D:%7.4f  Loss_G:%7.4f' % (
                epoch + 1, num_epochs, i + 1, total, d_loss.asnumpy(), g_loss.asnumpy()))
        D_losses.append(d_loss.asnumpy())
        G_losses.append(g_loss.asnumpy())

    # 每个epoch结束后，使用生成器生成一组图片
    generator.set_train(False)
    fixed_noise = ops.standard_normal((batch_size, nz, 1, 1))
    img = generator(fixed_noise)
    image_list.append(img.transpose(0, 2, 3, 1).asnumpy())

    # 保存网络模型参数为ckpt文件
    mindspore.save_checkpoint(generator, "./generator.ckpt")
    mindspore.save_checkpoint(discriminator, "./discriminator.ckpt")

结果显示

得到生成器和判别器训练迭代的损失函数：

plt.figure(figsize=(10, 5))
plt.title("Generator and Discriminator Loss During Training")
plt.plot(G_losses, label="G", color='blue')
plt.plot(D_losses, label="D", color='orange')
plt.xlabel("iterations")
plt.ylabel("Loss")
plt.legend()
plt.show()

显示生成的图像

import matplotlib.pyplot as plt
import matplotlib.animation as animation

def showGif(image_list):
    show_list = []
    fig = plt.figure(figsize=(8, 3), dpi=120)
    for epoch in range(len(image_list)):
        images = []
        for i in range(3):
            row = np.concatenate((image_list[epoch][i * 8:(i + 1) * 8]), axis=1)
            images.append(row)
        img = np.clip(np.concatenate((images[:]), axis=0), 0, 1)
        plt.axis("off")
        show_list.append([plt.imshow(img)])

    ani = animation.ArtistAnimation(fig, show_list, interval=1000, repeat_delay=1000, blit=True)
    ani.save('./dcgan.gif', writer='pillow', fps=1)

showGif(image_list)

可见随着训练次数的增加，图像质量也越来越好。

加载生成器网络模型参数文件来生成图像：

# 从文件中获取模型参数并加载到网络中
mindspore.load_checkpoint("./generator.ckpt", generator)

fixed_noise = ops.standard_normal((batch_size, nz, 1, 1))
img64 = generator(fixed_noise).transpose(0, 2, 3, 1).asnumpy()

fig = plt.figure(figsize=(8, 3), dpi=120)
images = []
for i in range(3):
    images.append(np.concatenate((img64[i * 8:(i + 1) * 8]), axis=1))
img = np.clip(np.concatenate((images[:]), axis=0), 0, 1)
plt.axis("off")
plt.imshow(img)
plt.show()

总结

DCGAN在判别器和生成器中加入了卷积和转置卷积层，随着迭代次数的增加，生成图像的质量也随之提高。