Pytorch學(xué)習(xí)筆記DCGAN極簡入門教程
1.圖片分類網(wǎng)絡(luò)
這是一個(gè)二分類網(wǎng)絡(luò),可以是alxnet ,vgg,resnet任何一個(gè),負(fù)責(zé)對圖片進(jìn)行二分類,區(qū)分圖片是真實(shí)圖片還是生成的圖片
2.圖片生成網(wǎng)絡(luò)
輸入是一個(gè)隨機(jī)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(gè)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(gè)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(diǎn)是生成網(wǎng)絡(luò)
代碼如下,其實(shí)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(gè)網(wǎng)絡(luò)都挺簡單。
真正的重點(diǎn)到了,怎么訓(xùn)練
每一個(gè)step分為三個(gè)步驟:
- 訓(xùn)練二分類網(wǎng)絡(luò)
1.輸入真實(shí)圖片,經(jīng)過二分類,希望判定為真實(shí)圖片,更新二分類網(wǎng)絡(luò)
2.輸入噪聲,進(jìn)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(jìn)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(shí)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(xì)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!
相關(guān)文章
Python模塊結(jié)構(gòu)與布局操作方法實(shí)例分析
這篇文章主要介紹了Python模塊結(jié)構(gòu)與布局操作方法,結(jié)合實(shí)例形式分析了Python模塊與布局的相關(guān)概念、使用方法與相關(guān)注意事項(xiàng),需要的朋友可以參考下2017-07-07Python開發(fā)之基于模板匹配的信用卡數(shù)字識別功能
這篇文章主要介紹了基于模板匹配的信用卡數(shù)字識別功能,本文給大家介紹的非常詳細(xì),具有一定的參考借鑒價(jià)值,需要的朋友可以參考下2020-01-01python實(shí)現(xiàn)貪吃蛇雙人大戰(zhàn)
這篇文章主要為大家詳細(xì)介紹了python實(shí)現(xiàn)貪吃蛇雙人大戰(zhàn),文中示例代碼介紹的非常詳細(xì),具有一定的參考價(jià)值,感興趣的小伙伴們可以參考一下2020-04-04Python中的遠(yuǎn)程調(diào)試與性能優(yōu)化技巧分享
Python 是一種簡單易學(xué)、功能強(qiáng)大的編程語言,廣泛應(yīng)用于各種領(lǐng)域,包括網(wǎng)絡(luò)編程、數(shù)據(jù)分析、人工智能等,在開發(fā)過程中,我們經(jīng)常會遇到需要遠(yuǎn)程調(diào)試和性能優(yōu)化的情況,本文將介紹如何利用遠(yuǎn)程調(diào)試工具和性能優(yōu)化技巧來提高 Python 應(yīng)用程序的效率和性能2024-05-05Python實(shí)現(xiàn)將字典內(nèi)容寫入json文件
這篇文章主要為大家詳細(xì)介紹了如何利用Python語言實(shí)現(xiàn)將字典內(nèi)容寫入json文件,文中的示例代碼講解詳細(xì),感興趣的小伙伴可以了解一下2022-08-08python 系統(tǒng)調(diào)用的實(shí)例詳解
這篇文章主要介紹了python 系統(tǒng)調(diào)用的實(shí)例詳解的相關(guān)資料,需要的朋友可以參考下2017-07-07