GAN网络简单应用——MNISTS数据集合2

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

# 创建保存生成图像的目录
os.makedirs("images1", exist_ok=True)

# 解析命令行参数
parser = argparse.ArgumentParser()
parser.add_argument("--n_epochs", type=int, default=100, help="number of epochs of training")
parser.add_argument("--batch_size", type=int, default=128, 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=8, 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("--img_size", type=int, default=28, 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 samples")
opt = parser.parse_args()
print(opt)

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

# 检查是否有可用的 GPU
#cuda = True if torch.cuda.is_available() else False
device = 'cuda' if torch.cuda.is_available() else 'cpu'
# ----------------
# 模型定义
# ----------------

# 生成器模型
class Generator(nn.Module):
    def __init__(self):
        super(Generator, self).__init__()
        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, 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, z):
        img = self.model(z)
        img = img.view(img.size(0), *img_shape)
        return img

# 判别器模型
class Discriminator(nn.Module):
    def __init__(self):
        super(Discriminator, self).__init__()

        self.model = nn.Sequential(
            nn.Linear(int(np.prod(img_shape)), 512),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Linear(512, 256),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Linear(256, 1),
            nn.Sigmoid(),
        )

    def forward(self, img):
        img_flat = img.view(img.size(0), -1)
        validity = self.model(img_flat)
        return validity

# 二元交叉熵损失函数
adversarial_loss = torch.nn.BCELoss()

# 初始化生成器和判别器
generator = Generator()
discriminator = Discriminator()

# 将模型移动到GPU上（如果可用）
generator.to(device)
discriminator.to(device)
adversarial_loss.to(device)
# 配置数据加载器
os.makedirs("./data/mnist", exist_ok=True)
transform = transforms.Compose(
    [transforms.Resize(opt.img_size), transforms.ToTensor(), transforms.Normalize([0.5], [0.5])]
)
train_ds = datasets.MNIST("./data/mnist", train=True, transform=transform, download=False)
dataloader = torch.utils.data.DataLoader(
    train_ds,
    batch_size=opt.batch_size,
    shuffle=True,
)

# 优化器
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))

# 生成一个在设备上（GPU或CPU）随机生成的输入张量
test_input = torch.randn([16, 100], device=device)
#Tensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor

def loss_show(D_loss, G_loss):
    plt.figure(figsize=(8, 8))
    if len(D_loss) == len(G_loss):
        step = len(D_loss)
    else:
        print("Warning: Lengths of D_loss and G_loss are not equal.")
        exit()
    plt.plot(range(0, step), D_loss, label='Discriminator Loss', color='red')
    plt.plot(range(0, step), G_loss, label='Generator Loss', color='blue')
    plt.legend(['Discriminator Loss', 'Generator Loss'])
    plt.xlabel('step', fontsize=14)
    plt.ylabel('loss value', fontsize=14)
    # 在每个点的位置添加文本标签
    #for i, (x, y_d, y_g) in enumerate(zip(range(0, step), D_loss, G_loss)):
        #plt.text(x, y_d, f'({y_d:.2f})', fontsize=8, color='red', ha='right', va='bottom')
        #plt.text(x, y_g, f'({y_g:.3f})', fontsize=8, color='red', ha='right', va='bottom')
    plt.title('Discriminator and Generator Loss Over Steps')
    plt.show()

D_loss =[]
G_loss =[]
# ---------
#  训练循环
# ---------
for epoch in range(100):
    d_epoch_loss,g_epoch_loss=0,0
    count = len(dataloader)
    for i, (imgs, _) in enumerate(dataloader):

        # Adversarial ground truths
        # 为真实样本和生成样本创建标签
        valid = torch.full((imgs.size(0), 1), 1.0, dtype=torch.float32, requires_grad=False).to(device)
        fake = torch.full((imgs.size(0), 1), 0.0, dtype=torch.float32, requires_grad=False).to(device)
        # 配置输入
        real_imgs = imgs.to(device)
        # -----------------
        #  训练生成器
        # -----------------

        optimizer_G.zero_grad()

        # 生成潜在空间中的噪声向量
        z = torch.randn((imgs.shape[0], opt.latent_dim)).to(device)
        # 生成图像
        gen_imgs = generator(z)

        # 计算生成器的损失
        g_loss = adversarial_loss(discriminator(gen_imgs), valid)

        g_loss.backward()
        optimizer_G.step()

        # ---------------------
        #  训练判别器
        # ---------------------

        optimizer_D.zero_grad()

        # 计算判别器对真实样本的损失
        real_loss = adversarial_loss(discriminator(real_imgs), valid)
        # 计算判别器对生成样本的损失，将生成器的输出张量分离以避免梯度传播到生成器模型
        fake_loss = adversarial_loss(discriminator(gen_imgs.detach()), fake)
        # 判别器总体损失为真实样本损失和生成样本损失的平均值
        d_loss = (real_loss + fake_loss) / 2

        d_loss.backward()
        optimizer_D.step()
        # 一个epoch中总的loss
        with torch.no_grad():
            d_epoch_loss += d_loss
            g_epoch_loss += g_loss

        batches_done = epoch * len(dataloader) + i
        # 每隔一定的迭代次数保存生成器生成的图像
        if batches_done % opt.sample_interval == 0:
            save_image(gen_imgs.data[:25], "images1/%d.png" % batches_done, nrow=5, normalize=True)

            with torch.no_grad():
                d_epoch_loss /= count
                g_epoch_loss /= count
                D_loss.append(d_epoch_loss.detach().cpu().numpy())
                G_loss.append(g_epoch_loss.detach().cpu().numpy())
                print(f'Epoch: {epoch},D_loss: {D_loss[epoch].item():.3f},G_loss: {G_loss[epoch].item():.3f}')

loss_show(D_loss,G_loss)