Pytorch學(xué)習(xí)筆記DCGAN極簡入門教程

更新時間：2021年09月07日 09:42:26 作者：xz1308579340

網(wǎng)上GAN的教程太多了，這邊也談一下自己的理解，本文給大家介紹一下GAN的兩部分組成，有需要的朋友可以借鑒參考下，希望能夠有所幫助

1.圖片分類網(wǎng)絡(luò)

這是一個二分類網(wǎng)絡(luò)，可以是alxnet ,vgg,resnet任何一個，負責(zé)對圖片進行二分類，區(qū)分圖片是真實圖片還是生成的圖片

2.圖片生成網(wǎng)絡(luò)

輸入是一個隨機噪聲，輸出是一張圖片，使用的是反卷積層

相信學(xué)過深度學(xué)習(xí)的都能寫出這兩個網(wǎng)絡(luò)，當(dāng)然如果你寫不出來，沒關(guān)系，有人替你寫好了

首先是圖片分類網(wǎng)絡(luò)：

簡單來說就是cnn+relu+sogmid，可以換成任何一個分類網(wǎng)絡(luò)，比如bgg,resnet等

class Discriminator(nn.Module):
    def __init__(self, ngpu):
        super(Discriminator, self).__init__()
        self.ngpu = ngpu
        self.main = nn.Sequential(
            # input is (nc) x 64 x 64
            nn.Conv2d(nc, ndf, 4, 2, 1, bias=False),
            nn.LeakyReLU(0.2, inplace=True),
            # state size. (ndf) x 32 x 32
            nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 2),
            nn.LeakyReLU(0.2, inplace=True),
            # state size. (ndf*2) x 16 x 16
            nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 4),
            nn.LeakyReLU(0.2, inplace=True),
            # state size. (ndf*4) x 8 x 8
            nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 8),
            nn.LeakyReLU(0.2, inplace=True),
            # state size. (ndf*8) x 4 x 4
            nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),
            nn.Sigmoid()
        )
    def forward(self, input):
        return self.main(input)

重點是生成網(wǎng)絡(luò)

代碼如下,其實就是反卷積+bn+relu

class Generator(nn.Module):
    def __init__(self, ngpu):
        super(Generator, self).__init__()
        self.ngpu = ngpu
        self.main = nn.Sequential(
            # input is Z, going into a convolution
            nn.ConvTranspose2d( nz, ngf * 8, 4, 1, 0, bias=False),
            nn.BatchNorm2d(ngf * 8),
            nn.ReLU(True),
            # state size. (ngf*8) x 4 x 4
            nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf * 4),
            nn.ReLU(True),
            # state size. (ngf*4) x 8 x 8
            nn.ConvTranspose2d( ngf * 4, ngf * 2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf * 2),
            nn.ReLU(True),
            # state size. (ngf*2) x 16 x 16
            nn.ConvTranspose2d( ngf * 2, ngf, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf),
            nn.ReLU(True),
            # state size. (ngf) x 32 x 32
            nn.ConvTranspose2d( ngf, nc, 4, 2, 1, bias=False),
            nn.Tanh()
            # state size. (nc) x 64 x 64
        )
    def forward(self, input):
        return self.main(input)

講道理，以上兩個網(wǎng)絡(luò)都挺簡單。

真正的重點到了，怎么訓(xùn)練

每一個step分為三個步驟：

訓(xùn)練二分類網(wǎng)絡(luò)
1.輸入真實圖片，經(jīng)過二分類，希望判定為真實圖片，更新二分類網(wǎng)絡(luò)
2.輸入噪聲，進過生成網(wǎng)絡(luò)，生成一張圖片，輸入二分類網(wǎng)絡(luò)，希望判定為虛假圖片，更新二分類網(wǎng)絡(luò)
訓(xùn)練生成網(wǎng)絡(luò)
3.輸入噪聲，進過生成網(wǎng)絡(luò)，生成一張圖片，輸入二分類網(wǎng)絡(luò)，希望判定為真實圖片，更新生成網(wǎng)絡(luò)

不多說直接上代碼

for epoch in range(num_epochs):
    # For each batch in the dataloader
    for i, data in enumerate(dataloader, 0):
        ############################
        # (1) Update D network: maximize log(D(x)) + log(1 - D(G(z)))
        ###########################
        ## Train with all-real batch
        netD.zero_grad()
        # Format batch
        real_cpu = data[0].to(device)
        b_size = real_cpu.size(0)
        label = torch.full((b_size,), real_label, device=device)
        # Forward pass real batch through D
        output = netD(real_cpu).view(-1)
        # Calculate loss on all-real batch
        errD_real = criterion(output, label)
        # Calculate gradients for D in backward pass
        errD_real.backward()
        D_x = output.mean().item()
        ## Train with all-fake batch
        # Generate batch of latent vectors
        noise = torch.randn(b_size, nz, 1, 1, device=device)
        # Generate fake image batch with G
        fake = netG(noise)
        label.fill_(fake_label)
        # Classify all fake batch with D
        output = netD(fake.detach()).view(-1)
        # Calculate D's loss on the all-fake batch
        errD_fake = criterion(output, label)
        # Calculate the gradients for this batch
        errD_fake.backward()
        D_G_z1 = output.mean().item()
        # Add the gradients from the all-real and all-fake batches
        errD = errD_real + errD_fake
        # Update D
        optimizerD.step()
        ############################
        # (2) Update G network: maximize log(D(G(z)))
        ###########################
        netG.zero_grad()
        label.fill_(real_label)  # fake labels are real for generator cost
        # Since we just updated D, perform another forward pass of all-fake batch through D
        output = netD(fake).view(-1)
        # Calculate G's loss based on this output
        errG = criterion(output, label)
        # Calculate gradients for G
        errG.backward()
        D_G_z2 = output.mean().item()
        # Update G
        optimizerG.step()
        # Output training stats
        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))
        # Save Losses for plotting later
        G_losses.append(errG.item())
        D_losses.append(errD.item())
        # Check how the generator is doing by saving G's output on fixed_noise
        if (iters % 500 == 0) or ((epoch == num_epochs-1) and (i == len(dataloader)-1)):
            with torch.no_grad():
                fake = netG(fixed_noise).detach().cpu()
            img_list.append(vutils.make_grid(fake, padding=2, normalize=True))
        iters += 1

以上就是Pytorch學(xué)習(xí)筆記DCGAN極簡入門教程的詳細內(nèi)容，更多關(guān)于Pytorch學(xué)習(xí)DCGAN入門教程的資料請關(guān)注腳本之家其它相關(guān)文章！

您可能感興趣的文章: