昇思25天学习打卡营第20天 | DCGAN生成漫画头像

内容介绍：

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。

判别器由分层的卷积层、BatchNorm层和LeakyReLU激活层组成。输入是3x64x64的图像，输出是该图像为真图像的概率。生成器则是由转置卷积层、BatchNorm层和ReLU激活层组成。输入是标准正态分布中提取出的隐向量𝑧，输出是3x64x64的RGB图像。

具体内容：

1. 导包

from download import download
import numpy as np
import mindspore.dataset as ds
import mindspore.dataset.vision as vision
import matplotlib.pyplot as plt
import mindspore as ms
from mindspore import nn, ops
from mindspore.common.initializer import Normal
import matplotlib.pyplot as plt
import matplotlib.animation as animation

2. 下载数据集

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

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

3. 参数定义

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

4. 数据集

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')

5. 可视化

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)

6. 网络搭建

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()

7. 判别器

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()

8. 损失函数

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

9. 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.')

10. 模型训练

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

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")

11. 结果显示

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()

12. 可视化展示

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)

通过实现DCGAN，我对生成对抗网络（GANs）的基本原理有了更深刻的理解。DCGAN通过引入卷积神经网络（CNN）到GAN中，使得生成的图像质量显著提升，特别是在处理图像数据如漫画头像时，其生成的纹理、色彩和细节都更加逼真自然。这一过程中，我深刻认识到网络结构设计、损失函数选择以及超参数调整对模型性能的重要影响。