生成对抗网络GAN学习

GAN网络学习路径

1、经典GAN网络的公式

 2、网络工作原理

(1)：从噪声z进行随机抽样，传入G网络，生成新数据G(z)和其概率分布Pg(G(z))

(2)：将真实数据和G生成的新数据一起传入D网络进行真假判别，通过sigmoid函数来输出判定类别

(3)：迭代优化D和G损失函数，根据D来调整G

(4)：直到D和G达到收敛，即D无法判断G产生数据的真假性，即Pg(G(z))已经非常逼近Pdata(x)

4、基于pytorch的代码实现

可以看代码讲解很详细：小白读基于pytorch的GAN网络代码 - 知乎

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

os.makedirs("images", exist_ok=True)

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 betwen image samples")
opt = parser.parse_args()
print(opt)

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

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


class Generator(nn.Module):
    def __init__(self):
        super(Generator, self).__init__()
#layers组成nn.liners,nn.leakyRelu（nn.batchNorm1d）
        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),#上面的opt中已经给出了参数
            *block(128, 256),
            *block(256, 512),
            *block(512, 1024),
            nn.Linear(1024, int(np.prod(img_shape))),#变成图片长*宽
            nn.Tanh()
        )

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


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


# Loss function
adversarial_loss = torch.nn.BCELoss()

# Initialize generator and discriminator
generator = Generator()
discriminator = Discriminator()

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

# Configure data loader
os.makedirs("./data/mnist", exist_ok=True)
dataloader = torch.utils.data.DataLoader(
    datasets.MNIST(
        "./data/mnist",
        train=True,
        download=True,
        transform=transforms.Compose(
            [transforms.Resize(opt.img_size), transforms.ToTensor(), transforms.Normalize([0.5], [0.5])]
        ),
    ),
    batch_size=opt.batch_size,
    shuffle=True,
)

# Optimizers
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

# ----------
#  Training
# ----------

for epoch in range(opt.n_epochs):
    for i, (imgs, _) in enumerate(dataloader):

        # Adversarial 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 input
        real_imgs = Variable(imgs.type(Tensor))

        # -----------------
        #  Train Generator
        # -----------------

        optimizer_G.zero_grad()

        # 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_imgs = generator(z)

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

        g_loss.backward()
        optimizer_G.step()

        # ---------------------
        #  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_imgs.detach()), fake)
        d_loss = (real_loss + fake_loss) / 2

        d_loss.backward()
        optimizer_D.step()

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

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

GAN的loss曲线，一般是d_loss前期数值小，g_loss前期数值大，之后d_loss慢慢变大，g_loss慢慢变小，从而达到对抗平衡。下图DCGAN网络训练损失曲线，详细看参考1。

原始GAN网络训练前期数据

Epoch[0/100],d_loss:0.257764,g_loss:3.051586 D real: 0.956534,D fake: 0.185285
Epoch[0/100],d_loss:0.018043,g_loss:4.845347 D real: 0.999024,D fake: 0.016838
Epoch[0/100],d_loss:0.259763,g_loss:5.910912 D real: 0.936510,D fake: 0.130793
Epoch[0/100],d_loss:0.137939,g_loss:5.873704 D real: 0.964222,D fake: 0.079805
Epoch[1/100],d_loss:0.036906,g_loss:3.868356 D real: 0.994611,D fake: 0.030603
Epoch[1/100],d_loss:0.172962,g_loss:6.150573 D real: 0.956688,D fake: 0.091935
Epoch[1/100],d_loss:0.171595,g_loss:7.379956 D real: 0.973292,D fake: 0.103041 

pix2pix制作自己的数据集

合并图片

python3 datasets/combine_A_and_B.py --fold_A datasets/ore/A --fold_B datasets/ore/B --fold_AB datasets/ore/AB

训练图片 

 python train.py --dataroot ./datasets/ore --name ore_pix2pix --model pix2pix --direction BtoA

参考

[1]https://pytorch.apachecn.org/#/docs/1.7/22