Gan /DCGan 生成对抗网络

GAN

 

Gan 神经网络来生成数据，可用于训练数据太少，生成伪数据来解决欠拟合问题

%matplotlib inline
import matplotlib.pyplot as plt
from torch.utils.data import DataLoader
from torch import nn
import numpy as np
from torch.autograd import Variable
import torch

class net_G(nn.Module):
    def __init__(self):
        super(net_G,self).__init__()
        self.model=nn.Sequential(
            nn.Linear(2,2),
        )
        self._initialize_weights()
    def forward(self,x):
        x=self.model(x)
        return x
    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m,nn.Linear):
                m.weight.data.normal_(0,0.02)
                m.bias.data.zero_()

class net_D(nn.Module):
    def __init__(self):
        super(net_D,self).__init__()
        self.model=nn.Sequential(
            nn.Linear(2,5),
            nn.Tanh(),
            nn.Linear(5,3),
            nn.Tanh(),
            nn.Linear(3,1),
            nn.Sigmoid()
        )
        self._initialize_weights()
    def forward(self,x):
        x=self.model(x)
        return x
    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m,nn.Linear):
                m.weight.data.normal_(0,0.02)
                m.bias.data.zero_()

# Saved in the d2l package for later use
def update_D(X,Z,net_D,net_G,loss,trainer_D):
    batch_size=X.shape[0]
    Tensor=torch.FloatTensor
    ones=Variable(Tensor(np.ones(batch_size))).view(batch_size,1)
    zeros = Variable(Tensor(np.zeros(batch_size))).view(batch_size,1)
    real_Y=net_D(X.float())
    fake_X=net_G(Z)
    fake_Y=net_D(fake_X)
    loss_D=(loss(real_Y,ones)+loss(fake_Y,zeros))/2
    loss_D.backward()
    trainer_D.step()
    return float(loss_D.sum())

def train(net_D,net_G,data_iter,num_epochs,lr_D,lr_G,latent_dim,data):
    loss=nn.BCELoss()
    Tensor=torch.FloatTensor
    trainer_D=torch.optim.Adam(net_D.parameters(),lr=lr_D)
    trainer_G=torch.optim.Adam(net_G.parameters(),lr=lr_G)
    plt.figure(figsize=(7,4))
    d_loss_point=[]
    g_loss_point=[]
    d_loss=0
    g_loss=0
    for epoch in range(1,num_epochs+1):
        d_loss_sum=0
        g_loss_sum=0
        batch=0
        for X in data_iter:
            batch+=1
            X=Variable(X)
            batch_size=X.shape[0]
            Z=Variable(Tensor(np.random.normal(0,1,(batch_size,latent_dim))))
            trainer_D.zero_grad()
            d_loss = update_D(X, Z, net_D, net_G, loss, trainer_D)
            d_loss_sum+=d_loss
            trainer_G.zero_grad()
            g_loss = update_G(Z, net_D, net_G, loss, trainer_G)
            g_loss_sum+=g_loss
        d_loss_point.append(d_loss_sum/batch)
        g_loss_point.append(g_loss_sum/batch)
    plt.ylabel('Loss', fontdict={'size': 14})
    plt.xlabel('epoch', fontdict={'size': 14})
    plt.xticks(range(0,num_epochs+1,3))
    plt.plot(range(1,num_epochs+1),d_loss_point,color='orange',label='discriminator')
    plt.plot(range(1,num_epochs+1),g_loss_point,color='blue',label='generator')
    plt.legend()
    plt.show()
    print(d_loss,g_loss)
    
    Z =Variable(Tensor( np.random.normal(0, 1, size=(100, latent_dim))))
    fake_X=net_G(Z).detach().numpy()
    plt.figure(figsize=(3.5,2.5))
    plt.scatter(data[:,0],data[:,1],color='blue',label='real')
    plt.scatter(fake_X[:,0],fake_X[:,1],color='orange',label='generated')
    plt.legend()
    plt.show()

 

DCGAN 卷积神经网络来生成伪数据，一般用于生成图片数据

import matplotlib.pyplot as plt
from torch.utils.data import DataLoader
from torch import nn
import numpy as np
from torch.autograd import Variable
import torch
from torchvision.datasets import ImageFolder
from torchvision.transforms import transforms
import zipfile
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
device=torch.device('gpu' if torch.cuda.is_available() else 'cpu')
class G_block(nn.Module):
    def __init__(self,in_channels, out_channels, kernel_size=4,
                strides=2, padding=1):
        super(G_block,self).__init__()
        self.conv2d_trans=nn.ConvTranspose2d(in_channels, out_channels, kernel_size=kernel_size,
                                             stride=strides, padding=padding, bias=False)
        self.batch_norm=nn.BatchNorm2d(out_channels,0.8)
        self.activation=nn.ReLU()
    def forward(self,x):
        return self.activation(self.batch_norm(self.conv2d_trans(x)))

class net_G(nn.Module):
    def __init__(self,in_channels):
        super(net_G,self).__init__()

        n_G=64
        self.model=nn.Sequential(
            G_block(in_channels,n_G*8,strides=1,padding=0),
            G_block(n_G*8,n_G*4),
            G_block(n_G*4,n_G*2),
            G_block(n_G*2,n_G),
            nn.ConvTranspose2d(
                n_G,3,kernel_size=4,stride=2,padding=1,bias=False
            ),
            nn.Tanh()
        )
    def forward(self,x):
        x=self.model(x)
        return x

class D_block(nn.Module):
    def __init__(self,in_channels,out_channels,kernel_size=4,strides=2,
                 padding=1,alpha=0.2):
        super(D_block,self).__init__()
        self.conv2d=nn.Conv2d(in_channels,out_channels,kernel_size,strides,padding,bias=False)
        self.batch_norm=nn.BatchNorm2d(out_channels,0.8)
        self.activation=nn.LeakyReLU(alpha)
    def forward(self,X):
        return self.activation(self.batch_norm(self.conv2d(X)))
        
        
class net_D(nn.Module):
    def __init__(self,in_channels):
        super(net_D,self).__init__()
        n_D=64
        self.model=nn.Sequential(
            D_block(in_channels,n_D),
            D_block(n_D,n_D*2),
            D_block(n_D*2,n_D*4),
            D_block(n_D*4,n_D*8)
        )
        self.conv=nn.Conv2d(n_D*8,1,kernel_size=4,bias=False)
        self.activation=nn.Sigmoid()
        # self._initialize_weights()
    def forward(self,x):
        x=self.model(x)
        x=self.conv(x)
        x=self.activation(x)
        return x
        
def update_D(X,Z,net_D,net_G,loss,trainer_D):
    batch_size=X.shape[0]
    ones=Variable(torch.FloatTensor(np.ones(batch_size,)).to(device),requires_grad=False).view(batch_size,1)
    zeros = Variable(Tensor(np.zeros(batch_size,)),requires_grad=False).view(batch_size,1)
    real_Y=net_D(X).view(batch_size,-1)
    fake_X=net_G(Z)
    fake_Y=net_D(fake_X).view(batch_size,-1)
    loss_D=(loss(real_Y,ones)+loss(fake_Y,zeros))/2
    loss_D.backward()
    trainer_D.step()
    return float(loss_D.sum())
    
def update_G(Z,net_D,net_G,loss,trainer_G):
    batch_size=Z.shape[0]
    ones=Variable(torch.FloatTensor(np.ones((batch_size,))).to(device),requires_grad=False).view(batch_size,1)
    fake_X=net_G(Z)
    fake_Y=net_D(fake_X).view(batch_size,-1)
    loss_G=loss(fake_Y,ones)
    loss_G.backward()
    trainer_G.step()
    return float(loss_G.sum())


def train(net_D,net_Z,data_iter,num_epochs,lr,latent_dim):
    loss=nn.BCELoss()
    trainer_D=torch.optim.Adam(net_D.parameters(),lr=lr,betas=(0.9,0.999))
    trainer_G=torch.optim.Adam(net_D.parameters(),lr=lr,betas=(0.9,0.999))
    plt.figure(figsize=(12,12))
    g_loss=0.0
    d_loss=0.0
    g_update_loss=[]
    d_update_loss=[]
    
    for eopch in (1,num_epochs+1):
        batch=0
        g_loss_sum=0.0
        d_loss_sum=0.0
        for X in data_iter:
            batch+=1
            X=X[:][0]
            X=Variable(X.type(Tensor))
            X=X.to(device)
            batch_size=X.shape[0]
            real_Y=net_D(X)
            Z=Variable(torch.FloatTensor(np.random.normal(0,1,(batch_size,latent_dim,1,1))))
            trainer_G.zero_grad()
            g_loss=update_G(Z,net_D,net_G,loss,trainer_G)
            g_loss_sum+=g_loss
            g_loss.backward()
            trainer_D.zero_grad()
            d_loss=update_D(X,Z,net_D,net_G,loss,trainer_D)
            d_loss_sum+=d_loss
        g_update_loss.append(g_loss_sum)
        d_update_loss.append(d_loss_sum)
        print(
            "[Epoch %d/%d]  [D loss: %f] [G loss: %f]"
            % (epoch, num_epochs,  d_loss_sum/batch_size,  g_loss_sum/batch_size)
        )
    plt.ylabel('Loss', fontdict={ 'size': 14})
    plt.xlabel('epoch', fontdict={ 'size': 14})
    plt.xticks(range(0,num_epochs+1,3))
    plt.plot(range(1,num_epochs+1),d_update_loss,color='orange',label='discriminator')
    plt.plot(range(1,num_epochs+1),g_update_loss,color='blue',label='generator')
    plt.legend()
    plt.show()
    print(d_loss,g_loss)

    Z = Variable(Tensor(np.random.normal(0, 1, size=(21, latent_dim, 1, 1))),requires_grad=False)
    fake_x = generator(Z)
    fake_x=fake_x.to(device).detach().numpy()
    plt.figure(figsize=(14,6))
    for i in range(21):
        im=np.transpose(fake_x[i])
        plt.subplot(3,7,i+1)
        plt.imshow(im)
    plt.show()