GAN网络手写数据集Pytorch实现

import argparse
import os
import numpy as np

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

#--------------------参数配置---------------------------
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: decy 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)

#--------------------1.准备数据集---------------------------
os.makedirs("images", exist_ok=True)
# Configure data loader
os.makedirs("../data/mnist", exist_ok=True)

# 图像预处理
transform=transforms.Compose([
    transforms.Resize(opt.img_size),
    transforms.ToTensor(),
    transforms.Normalize([0.5], [0.5])
])

mnist = datasets.MNIST(
    root="../data/mnist",
    train=True,
    transform=transform,
    download=True
)

data_loader = torch.utils.data.DataLoader(
    dataset=mnist,
    batch_size=opt.batch_size,
    shuffle=True,
)

# ---------------------2. 模型搭建--------------------------
# 生成器
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()   # -1to1
        )

    def forward(self, x):
        img = self.model(x)
        img = img.view(img.size(0), *img_shape)
        return img

# 辨别器
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

# -----------------------3. 损失函数和优化器-----------------------
adversarial_loss = torch.nn.BCELoss()

generator = Generator()
discriminator = Discriminator()

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

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

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))

Tensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor

# -----------------4. 训练------------------------------
for epoch in range(opt.n_epochs):
    for i, (imgs, _) in enumerate(data_loader):

        # ground truths
        valid = Variable(Tensor(imgs.size(0), 1).fill_(1.0), requires_grad=False)
        fake = Variable(Tensor(imgs.size(0), 1).fill_(0.0), requires_grad=False)

        #Configure imput
        real_imgs = Variable(imgs.type(Tensor))

        # Sample noise as generator input
        z = Variable(Tensor(np.random.normal(0, 1, (imgs.shape[0], opt.latent_dim))))

        # Generate a batch of images
        gen_images = generator(z)

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

        optimizer_D.zero_grad()

        # Measure discriminator's ability to classify real from generated samples
        real_loss = adversarial_loss(discriminator(real_imgs), valid)
        fake_loss = adversarial_loss(discriminator(gen_images.detach()), fake) # 冻结生成器梯度
        d_loss = (real_loss + fake_loss) / 2

        d_loss.backward()
        optimizer_D.step()

        # -------------------------
        #  Train Generator
        # -------------------------
        optimizer_G.zero_grad()

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

        g_loss.backward()
        optimizer_G.step()

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

        batches_done = epoch * len(data_loader) + i
        if batches_done % opt.sample_interval == 0:
            save_image(gen_images.data[:25], "images/%d.png" % batches_done, nrow=5, normalize=True)

torch.save(Generator.state_dict(), 'images/generator.pth')
torch.save(Discriminator.state_dict(), 'images/discriminator.pth')