简介:
GAN网络中文名:生成对抗网络。生成对抗网络其实是两个网络的组合:生成网络(Generator)负责生成模拟数据(造假);判别网络(Discriminator)负责判断输入的数据是真实的还是生成的(检验)。两个网络相互对抗中,不断更新优化自己的参数,直到达到平衡状态。
网络结构:
生成器(Generator):通过机器生成数据(大部分情况下是图像),最终目的是“骗过”判别器。诈骗成功。
判别器(Discriminator):判断这张图像是真实的还是机器生成的,目的是找出生成器做的“假数据”。练成火眼晶晶,段真假。
模型训练过程阐述:
这是一个生成器和判别器博弈的过程。生成器生成假数据,然后将生成的假数据和真数据都输入判别器,判别器要判断出哪些是真的哪些是假的。判别器第一次判别出来的肯定有很大的误差,然后我们根据误差来优化判别器。现在判别器水平提高了,生成器生成的数据很难再骗过判别器了,所以我们得反过来优化生成器,之后生成器水平提高了,然后反过来继续训练判别器,判别器水平又提高了,再反过来训练生成器,就这样循环往复,直到达到均衡。
损失函数:
生成网络和对抗网络的优化是如何实现的?继续往下走,这就涉及到两个核心的问题:神经网络的架构和损失函数 (loss function)。神经网络架构为全连接层结构这里不在赘述。主要介绍损失函数,它是能够实现优化(训练)的基本要素。
生成器损失函数
上式中,G 代表生成网络,D 代表判别网络,H 代表交叉熵,z 是输入随机数据。 是对生成数据的判断概率,1代表数据绝对真实,0代表数据绝对虚假。 代表判断结果与1的距离。显然生成网络想取得良好的效果,那就要做到,让判别器将生成数据判别为真数据(即与1的距离越小越好)。
判别器损失函数
上式中,X是真实数据,这里要注意的是,代表真实数据与1的距离,代表生成数据与0的距离。显然,识别网络要想取得良好的效果,那么就要做到,在它眼里,真实数据就是真实数据,生成数据就是虚假数据(即真实数据与1的距离小,生成数据与0的距离小)。
优化原理:生成网络和判别网络有了损失函数,就可以基于各自的损失函数,利用误差反向传播(Backpropagation)(BP)反向传播算法和最优化方法(如梯度下降法)来实现参数的调整),不断提高生成网络和判别网络的性能(最终生成网络和判别网络的成熟状态就是学习到了合理的映射函数)。
心得:
总结:生成对抗网络,类似于强化学习的思想,让两个模型相互竞争,在竞争中优化,直到达到最优平衡点。核心是损失函数和网络结构
代码:
生成器代码:
import torch.nn as nn
class Generator(nn.Module):
def __init__(self):
super(Generator, self).__init__()
def block(in_feat, out_feat, normalize=True):
layers = [nn.Linear(in_feat, out_feat)]
if normalize:
layers.append(nn.BatchNorm1d(out_feat, 0.8))
layers.append(nn.LeakyReLU(0.2, inplace=True))
return layers
self.model = nn.Sequential(
*block(opt.latent_dim, 128, normalize=False),
*block(128, 256),
*block(256, 512),
*block(512, 1024),
nn.Linear(1024, int(np.prod(img_shape))),
nn.Tanh()
)
def forward(self, z):
img = self.model(z)
img = img.view(img.size(0), *img_shape)
return img
判别器代码:
class Discriminator(nn.Module):
def __init__(self):
super(Discriminator, self).__init__()
self.model = nn.Sequential(
nn.Linear(int(np.prod(img_shape)), 512),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(512, 256),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(256, 1),
nn.Sigmoid(),
)
def forward(self, img):
img_flat = img.view(img.size(0), -1)
validity = self.model(img_flat)
return validity
损失函数:
采取交叉熵损失函数:
# Loss function
adversarial_loss = torch.nn.BCELoss()
加载数据集:
# Configure data loader
os.makedirs("./data/mnist", exist_ok=True) # 加载数据集,地址./data/mnist
dataloader = torch.utils.data.DataLoader(
datasets.MNIST(
"./data/mnist",
train=True,
download=True,
transform=transforms.Compose(
[transforms.Resize(opt.img_size), transforms.ToTensor(), transforms.Normalize([0.5], [0.5])]
),#transforms.Resize 将输入图像(PIL Image or Tensor)调整为给定的大小opt.img_size
),
batch_size=opt.batch_size,#opt.batch_size 设置batch默认为128
shuffle=True,
)
训练网络:
# Optimizers
optimizer_G = torch.optim.Adam(generator.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))
optimizer_D = torch.optim.Adam(discriminator.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))
Tensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor
# ----------
# Training
# ----------
for epoch in range(opt.n_epochs):
for i, (imgs, _) in enumerate(dataloader):
# Adversarial ground truths
valid = Variable(Tensor(imgs.size(0), 1).fill_(1.0), requires_grad=False)
fake = Variable(Tensor(imgs.size(0), 1).fill_(0.0), requires_grad=False)
# Configure input
real_imgs = Variable(imgs.type(Tensor))
# -----------------
# Train Generator
# -----------------
optimizer_G.zero_grad()
# Sample noise as generator input
z = Variable(Tensor(np.random.normal(0, 1, (imgs.shape[0], opt.latent_dim))))
# Generate a batch of images
gen_imgs = generator(z)
# Loss measures generator's ability to fool the discriminator
g_loss = adversarial_loss(discriminator(gen_imgs), valid)
g_loss.backward()
optimizer_G.step()
# ---------------------
# Train Discriminator
# ---------------------
optimizer_D.zero_grad()
# Measure discriminator's ability to classify real from generated samples
real_loss = adversarial_loss(discriminator(real_imgs), valid)
fake_loss = adversarial_loss(discriminator(gen_imgs.detach()), fake)
d_loss = (real_loss + fake_loss) / 2
d_loss.backward()
optimizer_D.step()
print(
"[Epoch %d/%d] [Batch %d/%d] [D loss: %f] [G loss: %f]"
% (epoch, opt.n_epochs, i, len(dataloader), d_loss.item(), g_loss.item())
)
先定义标签,Gan模型,所以标签需要重新定义,根据batch大小,valid标签大小为batch*1且值为1,fake标签大小为batch*1且值为0
valid = Variable(Tensor(imgs.size(0), 1).fill_(1.0), requires_grad=False)
fake = Variable(Tensor(imgs.size(0), 1).fill_(0.0), requires_grad=False)
生成器损失函数:生成器期望,判别器判断时,判断生成图像为真,即标签为1。更新梯度,优化模型。
g_loss = adversarial_loss(discriminator(gen_imgs), valid)
判别器损失函数:判别器期望,生成器生成的图片为假,标签为0;真实图片为真,标签为1。取两损失均值作为判别器损失函数,更新梯度,优化模型。
real_loss = adversarial_loss(discriminator(real_imgs), valid)
fake_loss = adversarial_loss(discriminator(gen_imgs.detach()), fake)
此为gan代码的基础版,但是网络思路一直是这个思路,希望大家能在此基础上设计出更好,更优的模型。
完整代码:
import argparse
import os
import numpy as np
import math
import torchvision.transforms as transforms
from torchvision.utils import save_image
from torch.utils.data import DataLoader
from torchvision import datasets
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F
import torch
os.makedirs("images", exist_ok=True)
parser = argparse.ArgumentParser()
parser.add_argument("--n_epochs", type=int, default=100, help="number of epochs of training")
parser.add_argument("--batch_size", type=int, default=128, help="size of the batches")
parser.add_argument("--lr", type=float, default=0.0002, help="adam: learning rate")
parser.add_argument("--b1", type=float, default=0.5, help="adam: decay of first order momentum of gradient")
parser.add_argument("--b2", type=float, default=0.999, help="adam: decay of first order momentum of gradient")
parser.add_argument("--n_cpu", type=int, default=8, help="number of cpu threads to use during batch generation")
parser.add_argument("--latent_dim", type=int, default=100, help="dimensionality of the latent space")
parser.add_argument("--img_size", type=int, default=28, help="size of each image dimension")
parser.add_argument("--channels", type=int, default=1, help="number of image channels")
parser.add_argument("--sample_interval", type=int, default=400, help="interval betwen image samples")
opt = parser.parse_args()
print(opt)
img_shape = (opt.channels, opt.img_size, opt.img_size)
cuda = True if torch.cuda.is_available() else False
class Generator(nn.Module):
def __init__(self):
super(Generator, self).__init__()
def block(in_feat, out_feat, normalize=True):
layers = [nn.Linear(in_feat, out_feat)]
if normalize:
layers.append(nn.BatchNorm1d(out_feat, 0.8))
layers.append(nn.LeakyReLU(0.2, inplace=True))
return layers
self.model = nn.Sequential(
*block(opt.latent_dim, 128, normalize=False),
*block(128, 256),
*block(256, 512),
*block(512, 1024),
nn.Linear(1024, int(np.prod(img_shape))),
nn.Tanh()
)
def forward(self, z):
img = self.model(z)
img = img.view(img.size(0), *img_shape)
return img
class Discriminator(nn.Module):
def __init__(self):
super(Discriminator, self).__init__()
self.model = nn.Sequential(
nn.Linear(int(np.prod(img_shape)), 512),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(512, 256),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(256, 1),
nn.Sigmoid(),
)
def forward(self, img):
img_flat = img.view(img.size(0), -1)
validity = self.model(img_flat)
return validity
# Loss function
adversarial_loss = torch.nn.BCELoss()
# Initialize generator and discriminator
generator = Generator()
discriminator = Discriminator()
if cuda:
generator.cuda()
discriminator.cuda()
adversarial_loss.cuda()
# Configure data loader
os.makedirs("./data/mnist", exist_ok=True)
dataloader = torch.utils.data.DataLoader(
datasets.MNIST(
"./data/mnist",
train=True,
download=True,
transform=transforms.Compose(
[transforms.Resize(opt.img_size), transforms.ToTensor(), transforms.Normalize([0.5], [0.5])]
),
),
batch_size=opt.batch_size,
shuffle=True,
)
# Optimizers
optimizer_G = torch.optim.Adam(generator.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))
optimizer_D = torch.optim.Adam(discriminator.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))
Tensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor
# ----------
# Training
# ----------
for epoch in range(opt.n_epochs):
for i, (imgs, _) in enumerate(dataloader):
# Adversarial ground truths
valid = Variable(Tensor(imgs.size(0), 1).fill_(1.0), requires_grad=False)
fake = Variable(Tensor(imgs.size(0), 1).fill_(0.0), requires_grad=False)
# Configure input
real_imgs = Variable(imgs.type(Tensor))
# -----------------
# Train Generator
# -----------------
optimizer_G.zero_grad()
# Sample noise as generator input
z = Variable(Tensor(np.random.normal(0, 1, (imgs.shape[0], opt.latent_dim))))
# Generate a batch of images
gen_imgs = generator(z)
# Loss measures generator's ability to fool the discriminator
g_loss = adversarial_loss(discriminator(gen_imgs), valid)
g_loss.backward()
optimizer_G.step()
# ---------------------
# Train Discriminator
# ---------------------
optimizer_D.zero_grad()
# Measure discriminator's ability to classify real from generated samples
real_loss = adversarial_loss(discriminator(real_imgs), valid)
fake_loss = adversarial_loss(discriminator(gen_imgs.detach()), fake)
d_loss = (real_loss + fake_loss) / 2
d_loss.backward()
optimizer_D.step()
print(
"[Epoch %d/%d] [Batch %d/%d] [D loss: %f] [G loss: %f]"
% (epoch, opt.n_epochs, i, len(dataloader), d_loss.item(), g_loss.item())
)
参考: