使用PyTorch生成新图像

Question

我正在研究GAN我已经完成了一门课程,它给了我一个程序的例子,该程序根据输入的例子生成图像.

这个例子可以在这里找到:

https://github.com/davidsonmizael/gan

所以我决定使用它来生成基于面部正面照片数据集的新图像,但我没有取得任何成功.与上面的示例不同,代码仅生成噪声,而输入具有实际图像.

实际上我没有任何关于我应该改变什么以使代码指向正确方向并从图像中学习的线索.我没有更改示例中提供的代码的单个值,但它不起作用.

如果有人能帮助我理解这一点,并指出我正确的方向将是非常有帮助的.提前致谢.

我的判断者:

class D(nn.Module):

    def __init__(self):
        super(D, self).__init__()
        self.main = nn.Sequential(
                nn.Conv2d(3, 64, 4, 2, 1, bias = False),
                nn.LeakyReLU(0.2, inplace = True),
                nn.Conv2d(64, 128, 4, 2, 1, bias = False),
                nn.BatchNorm2d(128),
                nn.LeakyReLU(0.2, inplace = True),
                nn.Conv2d(128, 256, 4, 2, 1, bias = False),
                nn.BatchNorm2d(256),
                nn.LeakyReLU(0.2, inplace = True),
                nn.Conv2d(256, 512, 4, 2, 1, bias = False),
                nn.BatchNorm2d(512),
                nn.LeakyReLU(0.2, inplace = True),
                nn.Conv2d(512, 1, 4, 1, 0, bias = False),
                nn.Sigmoid()
                )

    def forward(self, input):
        return self.main(input).view(-1)

我的发电机:

class G(nn.Module):

    def __init__(self):
        super(G, self).__init__()
        self.main = nn.Sequential(
                nn.ConvTranspose2d(100, 512, 4, 1, 0, bias = False),
                nn.BatchNorm2d(512),
                nn.ReLU(True),
                nn.ConvTranspose2d(512, 256, 4, 2, 1, bias = False),
                nn.BatchNorm2d(256),
                nn.ReLU(True),
                nn.ConvTranspose2d(256, 128, 4, 2, 1, bias = False),
                nn.BatchNorm2d(128),
                nn.ReLU(True),
                nn.ConvTranspose2d(128, 64, 4, 2, 1, bias = False),
                nn.BatchNorm2d(64),
                nn.ReLU(True),
                nn.ConvTranspose2d(64, 3, 4, 2, 1, bias = False),
                nn.Tanh()
                )

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

我启动权重的功能:

def weights_init(m):
    classname = m.__class__.__name__
    if classname.find('Conv') != -1:
        m.weight.data.normal_(0.0, 0.02)
    elif classname.find('BatchNorm') != -1:
        m.weight.data.normal_(1.0, 0.02)
        m.bias.data.fill_(0)

完整代码可以在这里看到:

https://github.com/davidsonmizael/criminal-gan

25号纪元产生的噪音:

用真实图像输入:

Answer 1

您的示例代码（https://github.com/davidsonmizael/gan）给了我与您所展示的相同的声音。发电机的损耗下降得太快了。

有一些小问题，我什至不知道是什么-但是我想很容易自己找出差异。作为比较，也请看一下本教程： 50行PyTorch中的GAN

.... same as your code
print("# Starting generator and descriminator...")
netG = G()
netG.apply(weights_init)

netD = D()
netD.apply(weights_init)

if torch.cuda.is_available():
    netG.cuda()
    netD.cuda()

#training the DCGANs
criterion = nn.BCELoss()
optimizerD = optim.Adam(netD.parameters(), lr = 0.0002, betas = (0.5, 0.999))
optimizerG = optim.Adam(netG.parameters(), lr = 0.0002, betas = (0.5, 0.999))

epochs = 25

timeElapsed = []
for epoch in range(epochs):
    print("# Starting epoch [%d/%d]..." % (epoch, epochs))
    for i, data in enumerate(dataloader, 0):
        start = time.time()
        time.clock()  

        #updates the weights of the discriminator nn
        netD.zero_grad()

        #trains the discriminator with a real image
        real, _ = data

        if torch.cuda.is_available():
            inputs = Variable(real.cuda()).cuda()
            target = Variable(torch.ones(inputs.size()[0]).cuda()).cuda()
        else:
            inputs = Variable(real)
            target = Variable(torch.ones(inputs.size()[0]))

        output = netD(inputs)
        errD_real = criterion(output, target)
        errD_real.backward() #retain_graph=True

        #trains the discriminator with a fake image
        if torch.cuda.is_available():
            D_noise = Variable(torch.randn(inputs.size()[0], 100, 1, 1).cuda()).cuda()
            target = Variable(torch.zeros(inputs.size()[0]).cuda()).cuda()
        else:
            D_noise = Variable(torch.randn(inputs.size()[0], 100, 1, 1))
            target = Variable(torch.zeros(inputs.size()[0]))
        D_fake = netG(D_noise).detach()
        D_fake_ouput = netD(D_fake)
        errD_fake = criterion(D_fake_ouput, target)
        errD_fake.backward()

        # NOT:backpropagating the total error
        # errD = errD_real + errD_fake

        optimizerD.step()

    #for i, data in enumerate(dataloader, 0):

        #updates the weights of the generator nn
        netG.zero_grad()

        if torch.cuda.is_available():
            G_noise = Variable(torch.randn(inputs.size()[0], 100, 1, 1).cuda()).cuda()
            target = Variable(torch.ones(inputs.size()[0]).cuda()).cuda()
        else:
            G_noise = Variable(torch.randn(inputs.size()[0], 100, 1, 1))
            target = Variable(torch.ones(inputs.size()[0]))

        fake = netG(G_noise)
        G_output = netD(fake)
        errG  = criterion(G_output, target)

        #backpropagating the error
        errG.backward()
        optimizerG.step()


        if i % 50 == 0:
            #prints the losses and save the real images and the generated images
            print("# Progress: ")
            print("[%d/%d][%d/%d] Loss_D: %.4f Loss_G: %.4f" % (epoch, epochs, i, len(dataloader), errD_real.data[0], errG.data[0]))

            #calculates the remaining time by taking the avg seconds that every loop
            #and multiplying by the loops that still need to run
            timeElapsed.append(time.time() - start)
            avg_time = (sum(timeElapsed) / float(len(timeElapsed)))
            all_dtl = (epoch * len(dataloader)) + i
            rem_dtl = (len(dataloader) - i) + ((epochs - epoch) * len(dataloader))
            remaining =  (all_dtl - rem_dtl) * avg_time
            print("# Estimated remaining time: %s" % (time.strftime("%H:%M:%S", time.gmtime(remaining))))

        if i % 100 == 0:
            vutils.save_image(real, "%s/real_samples.png" % "./results", normalize = True)
            vutils.save_image(fake.data, "%s/fake_samples_epoch_%03d.png" % ("./results", epoch), normalize = True)

print ("# Finished.")

在CIFAR-10上经过25个纪元（批量大小256）后的结果：