PyTorch(二次元头像--GAN实战)

1.预处理函数（这里有一个问题，transforms.Normalize（）函数的使用）

有博主写了 https://blog.csdn.net/xys430381_1/article/details/85724668

2.定义鉴别器

计算方式参考上一张 迁移学习的内容。最后输出向量的类型为256*6*6.

同时每次卷积过后，进行批归一化（这点与传统的方式不一样）+LeaKy ReLU

        

 

 3.定义生成器（理解为鉴别器的逆过程，反卷积的过程）

       

4.训练（初始化参数）

      

 

def train(d,g,criterion,d_optimizer,g_optimizer,epochs=1,show_every=1000,print_every=10):
    iter_count = 0
    for epoch in range(epochs):
        
        for inputs,_ in trainloader:

            real_inputs = inputs

            fake_inputs = g(torch.randn(5,100))
            
            real_labels = torch.ones(real_inputs.size(0))
            fake_labels = torch.zeros(5)
            
            real_outputs = d(real_inputs)
            d_loss_real = criterion(real_outputs,real_labels)
            real_scores = real_outputs

            fake_outputs = d(fake_inputs)
            d_loss_fake = criterion(fake_outputs,fake_labels)
            fake_scores = fake_outputs


            d_loss = d_loss_real+d_loss_fake
            d_optimizer.zero_grad()
            d_loss.backward()
            d_optimizer.step()
        
            fake_inputs = g(torch.randn(5,100))
            outputs = d(fake_inputs)
            real_labels = torch.ones(outputs.size(0))
            g_loss = criterion(outputs,real_labels)
            
            g_optimizer.zero_grad()
            g_loss.backward()
            g_optimizer.step()

            if (iter_count % show_every == 0):
                print('Epoch:{},Iter: {}, D: {:.4}, G:{:.4}'.format(epoch,iter_count, d_loss.item(), g_loss.item()))
                picname = "Epoch_"+str(epoch)+"Iter_"+str(iter_count)
                imshow(torchvision.utils.make_grid(fake_inputs.data),picname)
                save_param(d,'d_model.pkl')
                save_param(g,'g_model.pkl')

            if (iter_count%print_every == 0):
                print('Epoch:{},Iter: {}, D: {:.4}, G:{:.4}'.format(epoch,iter_count, d_loss.item(), g_loss.item()))
            iter_count += 1
        
    print('Finished Training')

这里就是训练的过程：

 

          

最后训练就完事了，结果我没有完全跑出来，时间太长不想跑。

 

跑了一部分结果出来，大概是这样的效果啦！！