Pytorch实战3：DCGAN深度卷积对抗生成网络生成动漫头像

本文主要是介绍Pytorch实战3：DCGAN深度卷积对抗生成网络生成动漫头像，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

版权申明：本文章为本人原创内容，转载请注明出处，谢谢合作！

实验环境：

1.Pytorch 0.4.0
2.torchvision 0.2.1
3.Python 3.6
4.Win10+Pycharm
本项目是基于DCGAN的，代码是在《深度学习框架PyTorch：入门与实践》第七章的配套代码上做过大量修改过的。项目所用数据集获取：点击获取提取码：g5qa，感谢知乎用户何之源爬取的数据。请将下载的压缩包里的图片完整解压至data/face/目录下。整个项目的代码结构如下图：
这里写图片描述
其中data/face里是存放训练图片的，imgs/存放的是最终的训练结果，model.py是DCGAN的结构，train.py是主要的训练文件。

首先是，model.py:

import torch.nn as nn
# 定义生成器网络G
class NetG(nn.Module):def __init__(self, ngf, nz):super(NetG, self).__init__()# layer1输入的是一个100x1x1的随机噪声, 输出尺寸(ngf*8)x4x4self.layer1 = nn.Sequential(nn.ConvTranspose2d(nz, ngf * 8, kernel_size=4, stride=1, padding=0, bias=False),nn.BatchNorm2d(ngf * 8),nn.ReLU(inplace=True))# layer2输出尺寸(ngf*4)x8x8self.layer2 = nn.Sequential(nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),nn.BatchNorm2d(ngf * 4),nn.ReLU(inplace=True))# layer3输出尺寸(ngf*2)x16x16self.layer3 = nn.Sequential(nn.ConvTranspose2d(ngf * 4, ngf * 2, 4, 2, 1, bias=False),nn.BatchNorm2d(ngf * 2),nn.ReLU(inplace=True))# layer4输出尺寸(ngf)x32x32self.layer4 = nn.Sequential(nn.ConvTranspose2d(ngf * 2, ngf, 4, 2, 1, bias=False),nn.BatchNorm2d(ngf),nn.ReLU(inplace=True))# layer5输出尺寸 3x96x96self.layer5 = nn.Sequential(nn.ConvTranspose2d(ngf, 3, 5, 3, 1, bias=False),nn.Tanh())# 定义NetG的前向传播def forward(self, x):out = self.layer1(x)out = self.layer2(out)out = self.layer3(out)out = self.layer4(out)out = self.layer5(out)return out# 定义鉴别器网络D
class NetD(nn.Module):def __init__(self, ndf):super(NetD, self).__init__()# layer1 输入 3 x 96 x 96, 输出 (ndf) x 32 x 32self.layer1 = nn.Sequential(nn.Conv2d(3, ndf, kernel_size=5, stride=3, padding=1, bias=False),nn.BatchNorm2d(ndf),nn.LeakyReLU(0.2, inplace=True))# layer2 输出 (ndf*2) x 16 x 16self.layer2 = nn.Sequential(nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),nn.BatchNorm2d(ndf * 2),nn.LeakyReLU(0.2, inplace=True))# layer3 输出 (ndf*4) x 8 x 8self.layer3 = nn.Sequential(nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),nn.BatchNorm2d(ndf * 4),nn.LeakyReLU(0.2, inplace=True))# layer4 输出 (ndf*8) x 4 x 4self.layer4 = nn.Sequential(nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),nn.BatchNorm2d(ndf * 8),nn.LeakyReLU(0.2, inplace=True))# layer5 输出一个数(概率)self.layer5 = nn.Sequential(nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),nn.Sigmoid())# 定义NetD的前向传播def forward(self,x):out = self.layer1(x)out = self.layer2(out)out = self.layer3(out)out = self.layer4(out)out = self.layer5(out)return out

然后是，train.py:

import argparse
import torch
import torchvision
import torchvision.utils as vutils
import torch.nn as nn
from random import randint
from model import NetD, NetGparser = argparse.ArgumentParser()
parser.add_argument('--batchSize', type=int, default=64)
parser.add_argument('--imageSize', type=int, default=96)
parser.add_argument('--nz', type=int, default=100, help='size of the latent z vector')
parser.add_argument('--ngf', type=int, default=64)
parser.add_argument('--ndf', type=int, default=64)
parser.add_argument('--epoch', type=int, default=25, help='number of epochs to train for')
parser.add_argument('--lr', type=float, default=0.0002, help='learning rate, default=0.0002')
parser.add_argument('--beta1', type=float, default=0.5, help='beta1 for adam. default=0.5')
parser.add_argument('--data_path', default='data/', help='folder to train data')
parser.add_argument('--outf', default='imgs/', help='folder to output images and model checkpoints')
opt = parser.parse_args()
# 定义是否使用GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")#图像读入与预处理
transforms = torchvision.transforms.Compose([torchvision.transforms.Scale(opt.imageSize),torchvision.transforms.ToTensor(),torchvision.transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)), ])dataset = torchvision.datasets.ImageFolder(opt.data_path, transform=transforms)dataloader = torch.utils.data.DataLoader(dataset=dataset,batch_size=opt.batchSize,shuffle=True,drop_last=True,
)netG = NetG(opt.ngf, opt.nz).to(device)
netD = NetD(opt.ndf).to(device)criterion = nn.BCELoss()
optimizerG = torch.optim.Adam(netG.parameters(), lr=opt.lr, betas=(opt.beta1, 0.999))
optimizerD = torch.optim.Adam(netD.parameters(), lr=opt.lr, betas=(opt.beta1, 0.999))label = torch.FloatTensor(opt.batchSize)
real_label = 1
fake_label = 0for epoch in range(1, opt.epoch + 1):for i, (imgs,_) in enumerate(dataloader):# 固定生成器G，训练鉴别器DoptimizerD.zero_grad()## 让D尽可能的把真图片判别为1imgs=imgs.to(device)output = netD(imgs)label.data.fill_(real_label)label=label.to(device)errD_real = criterion(output, label)errD_real.backward()## 让D尽可能把假图片判别为0label.data.fill_(fake_label)noise = torch.randn(opt.batchSize, opt.nz, 1, 1)noise=noise.to(device)fake = netG(noise)  # 生成假图output = netD(fake.detach()) #避免梯度传到G，因为G不用更新errD_fake = criterion(output, label)errD_fake.backward()errD = errD_fake + errD_realoptimizerD.step()# 固定鉴别器D，训练生成器GoptimizerG.zero_grad()# 让D尽可能把G生成的假图判别为1label.data.fill_(real_label)label = label.to(device)output = netD(fake)errG = criterion(output, label)errG.backward()optimizerG.step()print('[%d/%d][%d/%d] Loss_D: %.3f Loss_G %.3f'% (epoch, opt.epoch, i, len(dataloader), errD.item(), errG.item()))vutils.save_image(fake.data,'%s/fake_samples_epoch_%03d.png' % (opt.outf, epoch),normalize=True)torch.save(netG.state_dict(), '%s/netG_%03d.pth' % (opt.outf, epoch))torch.save(netD.state_dict(), '%s/netD_%03d.pth' % (opt.outf, epoch))