昇思25天学习打卡营第22天 | DCGAN生成漫画头像-CSDN博客

本文链接：https://blog.csdn.net/qq_31254435/article/details/140647920

昇思25天学习打卡营第22天 | DCGAN生成漫画头像

文章目录

昇思25天学习打卡营第22天 | DCGAN生成漫画头像

DCGAN模型

深度卷积对抗生成网络（Depp Convolutional Generative Adversarial Networks, DCGAN）是GAN的直接拓展。区别在于DCGAN使用卷积和反卷积。

判别器：由分层的卷积层、BatchNorm层和LeakyReLU激活层组成。输入是 $3\times 64\times 64$ 的图像，输出是该图像为真图像的概率。
生成器：由反卷积层、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 $3\times 64\times 64$ 的RGB图像。

数据集

实验使用动漫头像数据集，共有70,171张动漫头像图片，大小均为 $96\times 96$ 。

数据下载和超参数

from download import download

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

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

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

创建数据集

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')

数据集可视化

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)

在这里插入图片描述

搭建网络

生成器

生成器 $G$ 是将隐向量 $z$ 映射到数据空间，由一系列Conv2dTranspose、BatchNorm2d和ReLU构成，输出数据经过tanh函数，使得返回 $[- 1, 1]$ 范围的数据。

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

判别器 $D$ 是一个二分类网络，由Conv2d、BatchNorm2d和LeakyReLU构成，最后通过Sigmoid激活函数得到最终概率。

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()

损失函数和优化器

使用二进制交叉熵损失函数BCELoss和Adam优化器：

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

# 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.')

模型训练

判别器：最大化 $\log D(x)+\log(1-D(G(z))$ ；
生成器：最小化 $\log(1-D(G(z)))$ 。

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

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")