self attention gan 的全部代码，包括数据载入、模型代码、训练代码以及测试代码

以下是一个简单的 Self-Attention GAN 的代码，包括数据载入、模型、训练和测试代码。

首先，我们需要导入必要的库：

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision.transforms as transforms
import torchvision.datasets as datasets
from torch.utils.data import DataLoader

接下来，我们需要定义一些超参数：

batch_size = 128
image_size = 64
nz = 100
ngf = 64
ndf = 64
num_epochs = 5
lr = 0.0002
beta1 = 0.5
ngpu = 1

然后，我们需要定义数据载入器：

dataset = datasets.ImageFolder(root='data',
                               transform=transforms.Compose([
                                   transforms.Resize(image_size),
                                   transforms.CenterCrop(image_size),
                                   transforms.ToTensor(),
                                   transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
                               ]))
dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True, num_workers=4)

接下来，我们需要定义生成器和判别器：

class Generator(nn.Module):
    def __init__(self):
        super(Generator, self).__init__()

        self.main = nn.Sequential(
            nn.ConvTranspose2d(nz, ngf * 8, 4, 1, 0, bias=False),
            nn.BatchNorm2d(ngf * 8),
            nn.ReLU(True),
            nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf * 4),
            nn.ReLU(True),
            nn.ConvTranspose2d(ngf * 4, ngf * 2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf * 2),
            nn.ReLU(True),
            nn.ConvTranspose2d(ngf * 2, ngf, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf),
            nn.ReLU(True),
            nn.ConvTranspose2d(ngf, 3, 4, 2, 1, bias=False),
            nn.Tanh()
        )

    def forward(self, input):
        return self.main(input)


class Discriminator(nn.Module):
    def __init__(self):
        super(Discriminator, self).__init__()

        self.main = nn.Sequential(
            nn.Conv2d(3, ndf, 4, 2, 1, bias=False),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 2),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 4),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 8),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),
            nn.Sigmoid()
        )

    def forward(self, input):
        return self.main(input)

接下来，我们需要初始化生成器和判别器：

device = torch.device("cuda:0" if (torch.cuda.is_available() and ngpu > 0) else "cpu")

netG = Generator().to(device)
netD = Discriminator().to(device)

if (device.type == 'cuda') and (ngpu > 1):
    netG = nn.DataParallel(netG, list(range(ngpu)))
    netD = nn.DataParallel(netD, list(range(ngpu)))

然后，我们需要定义损失函数和优化器：

criterion = nn.BCELoss()

fixed_noise = torch.randn(64, nz, 1, 1, device=device)

real_label = 1
fake_label = 0

optimizerD = optim.Adam(netD.parameters(), lr=lr, betas=(beta1, 0.999))
optimizerG = optim.Adam(netG.parameters(), lr=lr, betas=(beta1, 0.999))

最后，我们可以开始训练模型：

for epoch in range(num_epochs):
    for i, data in enumerate(dataloader, 0):
        netD.zero_grad()
        real_cpu = data[0].to(device)
        b_size = real_cpu.size(0)
        label = torch.full((b_size,), real_label, device=device)

        output = netD(real_cpu).view(-1)
        errD_real = criterion(output, label)
        errD_real.backward()
        D_x = output.mean().item()

        noise = torch.randn(b_size, nz, 1, 1, device=device)
        fake = netG(noise)
        label.fill_(fake_label)
        output = netD(fake.detach()).view(-1)
        errD_fake = criterion(output, label)
        errD_fake.backward()
        D_G_z1 = output.mean().item()
        errD = errD_real + errD_fake
        optimizerD.step()

        netG.zero_grad()
        label.fill_(real_label)
        output = netD(fake).view(-1)
        errG = criterion(output, label)
        errG.backward()
        D_G_z2 = output.mean().item()
        optimizerG.step()

        if i % 50 == 0:
            print('[%d/%d][%d/%d]\tLoss_D: %.4f\tLoss_G: %.4f\tD(x): %.4f\tD(G(z)): %.4f / %.4f'
                  % (epoch, num_epochs, i, len(dataloader),
                     errD.item(), errG.item(), D_x, D_G_z1, D_G_z2))

        if (epoch == 0) and (i == 0):
            torchvision.utils.save_image(real_cpu, 'real_samples.png', normalize=True)

        if i == len(dataloader) - 1:
            with torch.no_grad():
                fake = netG(fixed_noise).detach().cpu()
            torchvision.utils.save_image(fake, 'fake_samples_epoch_%03d.png' % epoch, normalize=True)

测试代码：

import matplotlib.pyplot as plt
import numpy as np

def show_generated_img_all():
    n_images=5
    rows = 1
    cols = 5
    noise = torch.randn(n_images, nz, 1, 1).to(device)
    fake_images = netG(noise)
    fig, axes = plt.subplots(rows, cols, figsize=(15,5))
    for i in range(rows):
        for j in range(cols):
            idx = i*cols+j
            axes[j].imshow(np.transpose(fake_images[idx].detach().cpu().numpy(), (1,2,0)))
            axes[j].axis('off')
    plt.show()

show_generated_img_all()

以上就是一个简单的 Self-Attention GAN 的代码。其中，数据载入器可以根据自己的数据集进行修改，超参数也可以根据需要进行调整。