第六课 GAN

最新推荐文章于 2024-11-09 21:51:15 发布

WangJue-tsinghua

最新推荐文章于 2024-11-09 21:51:15 发布

阅读量39

点赞数

分类专栏： pytorch学习文章标签： cnn 人工智能神经网络

本文链接：https://blog.csdn.net/qq_45679878/article/details/132819262

版权

pytorch学习专栏收录该内容

8 篇文章 0 订阅

订阅专栏

第六课 GAN

GAN：对抗生成网络

损失函数

adversarial_loss = torch.nn.BCELoss()
adversarial_loss = torch.nn.BCELWithLogitsLoss()  #会先对预测结果进行sigmoid操作

BCELoss计算公式（ $o$ 是预测值， $t$ 是标签0/1）
$loss(o,t)=-\frac{1}{n}\sum_i(t[i]*\log(o[i])+(1-t[i])*\log(1-o[i]))$

生成器网络模型（以MNIST为例）

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),  #编码器维数
            *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)    #[28,28,1]
        return img

判别器网络模型

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

生成器训练

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()

判别器训练

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()

CycleGan

创新点 1. 图像如何学习变化 2. 没有配对的图像

输入数据：只需要两组图像数据集即可，无需指定对应关系，例如马/斑马

网络结构

涉及到4种损失函数：G网络，D网络，Cycle（例如input_A和Cyclic_A），Identity（例如input_A和GeneratorB2A(input_A)）
D网络有点特别，采用PatchGAN

PatchGAN

不像普通的GAN网络输出的是一个预测值 $t$ ，而是一个 $N * N$ 的矩阵，需要基于感受野来计算损失
基于感受野在特征图上的预测结果，和标签（ $N * N$ 的矩阵）计算损失

生成网络模块

先进行卷积（图像大小越来越小，特征图数量越来越多），再进行反卷积（图像大小越来越大，特征图数量越来越少）

class ResnetGenerator(nn.Module):
    def __init__(self, input_nc, output_nc, ngf=64, norm_layer=nn.BatchNorm2d, use_dropout=False, n_blocks=6, padding_type='reflect'):
        """Construct a Resnet-based generator

        Parameters:
            input_nc (int)      -- the number of channels in input images
            output_nc (int)     -- the number of channels in output images
            ngf (int)           -- the number of filters in the last conv layer
            norm_layer          -- normalization layer
            use_dropout (bool)  -- if use dropout layers
            n_blocks (int)      -- the number of ResNet blocks
            padding_type (str)  -- the name of padding layer in conv layers: reflect | replicate | zero
        """
        assert(n_blocks >= 0)
        super(ResnetGenerator, self).__init__()
        if type(norm_layer) == functools.partial:
            use_bias = norm_layer.func == nn.InstanceNorm2d
        else:
            use_bias = norm_layer == nn.InstanceNorm2d

        model = [nn.ReflectionPad2d(3),
                 nn.Conv2d(input_nc, ngf, kernel_size=7, padding=0, bias=use_bias),
                 norm_layer(ngf),
                 nn.ReLU(True)]

        n_downsampling = 2
        for i in range(n_downsampling):  # add downsampling layers
            mult = 2 ** i
            model += [nn.Conv2d(ngf * mult, ngf * mult * 2, kernel_size=3, stride=2, padding=1, bias=use_bias),
                      norm_layer(ngf * mult * 2),
                      nn.ReLU(True)]

        mult = 2 ** n_downsampling
        for i in range(n_blocks):       # add ResNet blocks

            model += [ResnetBlock(ngf * mult, padding_type=padding_type, norm_layer=norm_layer, use_dropout=use_dropout, use_bias=use_bias)]
        print (model)
        for i in range(n_downsampling):  # add upsampling layers
            mult = 2 ** (n_downsampling - i)
            model += [nn.ConvTranspose2d(ngf * mult, int(ngf * mult / 2),
                                         kernel_size=3, stride=2,
                                         padding=1, output_padding=1,
                                         bias=use_bias),
                      norm_layer(int(ngf * mult / 2)),
                      nn.ReLU(True)]
        model += [nn.ReflectionPad2d(3)]
        model += [nn.Conv2d(ngf, output_nc, kernel_size=7, padding=0)]
        model += [nn.Tanh()]
        print (model)
        self.model = nn.Sequential(*model)

    def forward(self, input):
        """Standard forward"""
        return self.model(input)

判别网络模块

卷积： $(H*W*S)\rightarrow(N*N*C)\rightarrow(N*N*1)$ ，最后多一层卷积得到PatchGAN

class NLayerDiscriminator(nn.Module):
    def __init__(self, input_nc, ndf=64, n_layers=3, norm_layer=nn.BatchNorm2d):
        """Construct a PatchGAN discriminator

        Parameters:
            input_nc (int)  -- the number of channels in input images
            ndf (int)       -- the number of filters in the last conv layer
            n_layers (int)  -- the number of conv layers in the discriminator
            norm_layer      -- normalization layer
        """
        super(NLayerDiscriminator, self).__init__()
        if type(norm_layer) == functools.partial:  # no need to use bias as BatchNorm2d has affine parameters
            use_bias = norm_layer.func == nn.InstanceNorm2d
        else:
            use_bias = norm_layer == nn.InstanceNorm2d

        kw = 4
        padw = 1
        sequence = [nn.Conv2d(input_nc, ndf, kernel_size=kw, stride=2, padding=padw), nn.LeakyReLU(0.2, True)]
        nf_mult = 1
        nf_mult_prev = 1
        for n in range(1, n_layers):  # gradually increase the number of filters
            nf_mult_prev = nf_mult
            nf_mult = min(2 ** n, 8)
            sequence += [
                nn.Conv2d(ndf * nf_mult_prev, ndf * nf_mult, kernel_size=kw, stride=2, padding=padw, bias=use_bias),
                norm_layer(ndf * nf_mult),
                nn.LeakyReLU(0.2, True)
            ]

        nf_mult_prev = nf_mult
        nf_mult = min(2 ** n_layers, 8)
        sequence += [
            nn.Conv2d(ndf * nf_mult_prev, ndf * nf_mult, kernel_size=kw, stride=1, padding=padw, bias=use_bias),
            norm_layer(ndf * nf_mult),
            nn.LeakyReLU(0.2, True)
        ]

        sequence += [nn.Conv2d(ndf * nf_mult, 1, kernel_size=kw, stride=1, padding=padw)]  # output 1 channel prediction map
        self.model = nn.Sequential(*sequence)

    def forward(self, input):
        """Standard forward."""
        return self.model(input)

损失函数

GAN：MSE （例如生成器Input_A和GeneratorA2B(Input_A)）
Cycle：L1
Idt：L1

前向传播

def forward(self):
    """Run forward pass; called by both functions <optimize_parameters> and <test>."""
    self.fake_B = self.netG_A(self.real_A)  # G_A(A)
    self.rec_A = self.netG_B(self.fake_B)   # G_B(G_A(A))
    self.fake_A = self.netG_B(self.real_B)  # G_B(B)
    self.rec_B = self.netG_A(self.fake_A)   # G_A(G_B(B))

反向传播

训练生成器

def backward_G(self):
    """Calculate the loss for generators G_A and G_B"""
    lambda_idt = self.opt.lambda_identity
    lambda_A = self.opt.lambda_A
    lambda_B = self.opt.lambda_B
    # Identity loss
    if lambda_idt > 0:
        # G_A should be identity if real_B is fed: ||G_A(B) - B||
        self.idt_A = self.netG_A(self.real_B)
        self.loss_idt_A = self.criterionIdt(self.idt_A, self.real_B) * lambda_B * lambda_idt
        # G_B should be identity if real_A is fed: ||G_B(A) - A||
        self.idt_B = self.netG_B(self.real_A)
        self.loss_idt_B = self.criterionIdt(self.idt_B, self.real_A) * lambda_A * lambda_idt
    else:
        self.loss_idt_A = 0
        self.loss_idt_B = 0

    # GAN loss D_A(G_A(A))
    self.loss_G_A = self.criterionGAN(self.netD_A(self.fake_B), True)
    # GAN loss D_B(G_B(B))
    self.loss_G_B = self.criterionGAN(self.netD_B(self.fake_A), True)
    # Forward cycle loss || G_B(G_A(A)) - A||
    self.loss_cycle_A = self.criterionCycle(self.rec_A, self.real_A) * lambda_A
    # Backward cycle loss || G_A(G_B(B)) - B||
    self.loss_cycle_B = self.criterionCycle(self.rec_B, self.real_B) * lambda_B
    # combined loss and calculate gradients
    self.loss_G = self.loss_G_A + self.loss_G_B + self.loss_cycle_A + self.loss_cycle_B +
    			 self.loss_idt_A + self.loss_idt_B
    self.loss_G.backward()

训练判别器

def backward_D_basic(self, netD, real, fake):
    """Calculate GAN loss for the discriminator

        Parameters:
            netD (network)      -- the discriminator D
            real (tensor array) -- real images
            fake (tensor array) -- images generated by a generator

        Return the discriminator loss.
        We also call loss_D.backward() to calculate the gradients.
        """
    # Real
    pred_real = netD(real)
    loss_D_real = self.criterionGAN(pred_real, True)
    # Fake
    pred_fake = netD(fake.detach())
    loss_D_fake = self.criterionGAN(pred_fake, False)
    # Combined loss and calculate gradients
    loss_D = (loss_D_real + loss_D_fake) * 0.5
    loss_D.backward()
    return loss_D

VISDOM可视化（科学上网）

pip install visdom
python -m visdom.server