记录一下
上资源:(github),
基于Pytorch的条件对抗生成网络
条件对抗生成网络和生成对抗网络的区别在于,条件对抗网络生成器和鉴别器额外输入了条件信息(以minist为例,就是额外输入了标签),具体流程如下:
我主要研究其中的CGAN部分,所有代码如下:
import argparse
import os
import numpy as np
import math
import matplotlib.pyplot as plt
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=200, help="number of epochs of training")
parser.add_argument("--batch_size", type=int, default=64, 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=4, 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("--n_classes", type=int, default=10, help="number of classes for dataset")
parser.add_argument("--img_size", type=int, default=32, 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 between image sampling")
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__()
self.label_emb = nn.Embedding(opt.n_classes, opt.n_classes)
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 + opt.n_classes, 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, noise, labels):
# Concatenate label embedding and image to produce input
gen_input = torch.cat((self.label_emb(labels), noise), -1)
img = self.model(gen_input)
img = img.view(img.size(0), *img_shape)
return img
class Discriminator(nn.Module):
def __init__(self):
super(Discriminator, self).__init__()
self.label_embedding = nn.Embedding(opt.n_classes, opt.n_classes)
self.model = nn.Sequential(
nn.Linear(opt.n_classes + int(np.prod(img_shape)), 512),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(512, 512),
nn.Dropout(0.4),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(512, 512),
nn.Dropout(0.4),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(512, 1),
)
def forward(self, img, labels):
# Concatenate label embedding and image to produce input
d_in = torch.cat((img.view(img.size(0), -1), self.label_embedding(labels)), -1)
validity = self.model(d_in)
return validity
# Loss functions
adversarial_loss = torch.nn.MSELoss()
# 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))
FloatTensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor
LongTensor = torch.cuda.LongTensor if cuda else torch.LongTensor
def sample_image(n_row, batches_done):
"""Saves a grid of generated digits ranging from 0 to n_classes"""
# Sample noise
z = Variable(FloatTensor(np.random.normal(0, 1, (n_row ** 2, opt.latent_dim))))
# Get labels ranging from 0 to n_classes for n rows
labels = np.array([num for _ in range(n_row) for num in range(n_row)])
labels = Variable(LongTensor(labels))
gen_imgs = generator(z, labels)
save_image(gen_imgs.data, "images/%d.png" % batches_done, nrow=n_row, normalize=True)
# ----------
# Training
# ----------
for epoch in range(opt.n_epochs):
for i, (imgs, labels) in enumerate(dataloader):
batch_size = imgs.shape[0]
# Adversarial ground truths
valid = Variable(FloatTensor(batch_size, 1).fill_(1.0), requires_grad=False)
fake = Variable(FloatTensor(batch_size, 1).fill_(0.0), requires_grad=False)
# Configure input
real_imgs = Variable(imgs.type(FloatTensor))
labels = Variable(labels.type(LongTensor))
# -----------------
# Train Generator
# -----------------
optimizer_G.zero_grad()
# Sample noise and labels as generator input
z = Variable(FloatTensor(np.random.normal(0, 1, (batch_size, opt.latent_dim))))
gen_labels = Variable(LongTensor(np.random.randint(0, opt.n_classes, batch_size)))
# Generate a batch of images
gen_imgs = generator(z, gen_labels)
# Loss measures generator's ability to fool the discriminator
validity = discriminator(gen_imgs, gen_labels)
g_loss = adversarial_loss(validity, valid)
g_loss.backward()
optimizer_G.step()
# ---------------------
# Train Discriminator
# ---------------------
optimizer_D.zero_grad()
# Loss for real images
validity_real = discriminator(real_imgs, labels)
d_real_loss = adversarial_loss(validity_real, valid)
# Loss for fake images
validity_fake = discriminator(gen_imgs.detach(), gen_labels)
d_fake_loss = adversarial_loss(validity_fake, fake)
# Total discriminator loss
d_loss = (d_real_loss + d_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())
)
batches_done = epoch * len(dataloader) + i
if batches_done % opt.sample_interval == 0:
sample_image(n_row=10, batches_done=batches_done)
一、代码:
import argparse
import os
import numpy as np
import math
import matplotlib.pyplot as plt
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
导入各种包,主要有argparse、os、numpy、torch。其中torch需要安装pytorch框架,没装的小伙伴,去看这篇博文:
安装教程
os.makedirs("images", exist_ok=True)
创建子文件夹,名称就是images,exist_ok取值为Ture时,已存在该文件夹,也不会报错。
parser = argparse.ArgumentParser()
parser.add_argument("--n_epochs", type=int, default=200, help="number of epochs of training")
parser.add_argument("--batch_size", type=int, default=64, 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=4, 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("--n_classes", type=int, default=10, help="number of classes for dataset")
parser.add_argument("--img_size", type=int, default=32, 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 between image sampling")
opt = parser.parse_args()
print(opt)
初始化参数,如rpoch次数,batch_size的大小等,sample_interval表示后续间隔保存CGAN图片的保存间隔。
img_shape = (opt.channels, opt.img_size, opt.img_size)
cuda = True if torch.cuda.is_available() else False
img_shape表示图片的大小,维度
cuda表示是否具备GPU加速的条件。
class Generator(nn.Module):
def __init__(self):
super(Generator, self).__init__()
self.label_emb = nn.Embedding(opt.n_classes, opt.n_classes)
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 + opt.n_classes, 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, noise, labels):
# Concatenate label embedding and image to produce input
gen_input = torch.cat((self.label_emb(labels), noise), -1)
img = self.model(gen_input)
img = img.view(img.size(0), *img_shape)
return img
创建生成器类
class Discriminator(nn.Module):
def __init__(self):
super(Discriminator, self).__init__()
self.label_embedding = nn.Embedding(opt.n_classes, opt.n_classes)
self.model = nn.Sequential(
nn.Linear(opt.n_classes + int(np.prod(img_shape)), 512),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(512, 512),
nn.Dropout(0.4),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(512, 512),
nn.Dropout(0.4),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(512, 1),
)
def forward(self, img, labels):
# Concatenate label embedding and image to produce input
d_in = torch.cat((img.view(img.size(0), -1), self.label_embedding(labels)), -1)
validity = self.model(d_in)
return validity
创建鉴别器类
# Loss functions
adversarial_loss = torch.nn.MSELoss()
# Initialize generator and discriminator
generator = Generator()
discriminator = Discriminator()
if cuda:
generator.cuda()
discriminator.cuda()
adversarial_loss.cuda()
adversarial_loss为损失函数,
generator,discriminator分别为生成器和鉴别器,
if cuda表示如果可以进行GPU加速,则在GPU内建立生成器、鉴别器和损失函数,
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,
)
下载数据,并保存
# 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))
FloatTensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor
LongTensor = torch.cuda.LongTensor if cuda else torch.LongTensor
优化器初始化,optimizer_G是生成器的优化函数部分,optimizer_D是鉴别器的
def sample_image(n_row, batches_done):
"""Saves a grid of generated digits ranging from 0 to n_classes"""
# Sample noise
z = Variable(FloatTensor(np.random.normal(0, 1, (n_row ** 2, opt.latent_dim))))
# Get labels ranging from 0 to n_classes for n rows
labels = np.array([num for _ in range(n_row) for num in range(n_row)])
labels = Variable(LongTensor(labels))
gen_imgs = generator(z, labels)
save_image(gen_imgs.data, "images/%d.png" % batches_done, nrow=n_row, normalize=True)
这是一个生成网格图片的函数。
# Adversarial ground truths
valid = Variable(FloatTensor(batch_size, 1).fill_(1.0), requires_grad=False)
fake = Variable(FloatTensor(batch_size, 1).fill_(0.0), requires_grad=False)
# Configure input
real_imgs = Variable(imgs.type(FloatTensor))
labels = Variable(labels.type(LongTensor))
初始配置。
# -----------------
# Train Generator
# -----------------
optimizer_G.zero_grad()
# Sample noise and labels as generator input
z = Variable(FloatTensor(np.random.normal(0, 1, (batch_size, opt.latent_dim))))
gen_labels = Variable(LongTensor(np.random.randint(0, opt.n_classes, batch_size)))
# Generate a batch of images
gen_imgs = generator(z, gen_labels)
# Loss measures generator's ability to fool the discriminator
validity = discriminator(gen_imgs, gen_labels)
g_loss = adversarial_loss(validity, valid)
g_loss.backward()
optimizer_G.step()
训练生成器,先进行梯度归零,参考 这篇文章。接着,生成随机噪声z,单个样本的随机噪声为向量,这里的z大小为batch_size乘以单个样本的随机噪声,gen_labels表示随机生成的条件。然后,gen_imgs表示生成器根据随机噪声z和随机条件生成的样本数据,validity表示鉴别器根据随机图片和随机条件计算获得准确率,g_loss表示损失,衡量生成器的损失大小。g_loss.backward()表示反向传播计算,计算梯度,optimizer_G.step()表示计算更新参数(这个个解释可能有争议,具体没深入)。
# ---------------------
# Train Discriminator
# ---------------------
optimizer_D.zero_grad()
# Loss for real images
validity_real = discriminator(real_imgs, labels)
d_real_loss = adversarial_loss(validity_real, valid)
# Loss for fake images
validity_fake = discriminator(gen_imgs.detach(), gen_labels)
d_fake_loss = adversarial_loss(validity_fake, fake)
# Total discriminator loss
d_loss = (d_real_loss + d_fake_loss) / 2
d_loss.backward()
optimizer_D.step()
这部分是训练鉴别器,开始进行鉴别器的梯度置零,计算真实样本的真实率和误差,再计算生成样本的错误率和误差,总的误差取平均,进行反向传播计算,计算梯度,更新鉴别器的参数。
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())
)
打印输出训练的进度,鉴别器的损失和生成器的损失,
batches_done = epoch * len(dataloader) + i
if batches_done % opt.sample_interval == 0:
sample_image(n_row=10, batches_done=batches_done)
输出每隔opt.sample_interval的样本图片。
附上原文的伪代码流程:
其中,注意到,这个流程是先更新K次鉴别器,再更新1次生成器,我理解的鉴别器训练次数多一点,对图片样本是否是真实样本判断更准确一些,这样生成器生成的图片就会越逼近于真是样本。不过在源码中,k的值为1,即训练一次生成器,训练一次鉴别器。
参考文献:
1、Mirza M, Osindero S. Conditional generative adversarial nets[J]. arXiv preprint arXiv:1411.1784, 2014.
2、Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[J]. Advances in neural information processing systems, 2014, 27.