前言
- 由于本人水平有限,难免出现错漏,敬请批评改正。
- 更多精彩内容,可点击进入人工智能知识点专栏、Python日常小操作专栏、OpenCV-Python小应用专栏、YOLO系列专栏、自然语言处理专栏或我的个人主页查看
- 基于DETR的人脸伪装检测
- YOLOv7训练自己的数据集(口罩检测)
- YOLOv8训练自己的数据集(足球检测)
- YOLOv5:TensorRT加速YOLOv5模型推理
- YOLOv5:IoU、GIoU、DIoU、CIoU、EIoU
- 玩转Jetson Nano(五):TensorRT加速YOLOv5目标检测
- YOLOv5:添加SE、CBAM、CoordAtt、ECA注意力机制
- YOLOv5:yolov5s.yaml配置文件解读、增加小目标检测层
- Python将COCO格式实例分割数据集转换为YOLO格式实例分割数据集
- YOLOv5:使用7.0版本训练自己的实例分割模型(车辆、行人、路标、车道线等实例分割)
- 使用Kaggle GPU资源免费体验Stable Diffusion开源项目
相关介绍
对抗生成网络(Adversarial Generative Networks,简称GANs)是由伊恩·古德费洛(Ian Goodfellow)等人在2014年提出的深度学习框架,主要用于无监督学习中的数据生成任务。GAN的设计灵感来源于博弈论中的极小极大游戏,在机器学习领域开辟了一种全新的生成模型方法。
GAN包含两个主要组成部分:
生成器(Generator, G):
- 生成器G是一个神经网络,它的功能是从随机噪声向量(通常来自高斯分布或其他先验分布)出发,通过一系列变换来生成新的数据样本,这些样本应该尽可能接近于训练数据的真实分布。
- G的目标是尽可能地“欺骗”判别器,使其无法区分生成的数据和真实数据。
判别器(Discriminator, D):
- 判别器D也是一个神经网络,它的作用是接收输入的样本,并将其分类为“真”(来自真实数据分布)或“假”(来自生成器产生的分布)。
- D的目标是准确地区分真实数据和伪造数据,从而提高自身鉴别能力。
训练过程中,GAN采用了极小极大博弈策略,具体步骤如下:
- 先固定判别器参数,更新生成器参数以使得生成的数据更有可能被判别器误认为真实数据;
- 再固定生成器参数,更新判别器参数以更好地区分真实数据和生成器生成的伪数据。
这种交替优化的方式促使两个网络性能不断提升,直到达到纳什均衡,此时生成器能够生成非常逼真的新样本,而判别器再也无法有效区分真实数据和生成数据。
GAN在图像生成、图像到图像转换、视频生成、音频合成等多个领域都取得了显著成果,并且随着研究的深入,衍生出了许多改进版本和变体,比如条件GAN(Conditional GANs)、 Wasserstein GAN(WGAN)、CycleGAN等,进一步提高了生成效果并拓展了应用范围。
具体步骤
准备并读取数据集
以mnist数据集为例。
# 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,
)
定义生成器
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
定义判别器
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
定义损失函数
# Loss function
adversarial_loss = torch.nn.BCELoss()
定义优化器
# 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))
开始训练
# ----------
# 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
# 生成器损失,目的是生成的图像,逼近真是图像,是判别器认为是真
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
# 真实图像在判别器的目标函数损失,即判别器应该判为真
real_loss = adversarial_loss(discriminator(real_imgs), valid)
# 生成器生成出来的图像在判别器的目标函数损失,即判别器应该判为假
fake_loss = adversarial_loss(discriminator(gen_imgs.detach()), fake)
# 判别器损失,目的是判别生成的图像是假
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())
)
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())
)
batches_done = epoch * len(dataloader) + i
if batches_done % opt.sample_interval == 0:
save_image(gen_imgs.data[:25], "images/%d.png" % batches_done, nrow=5, normalize=True)
训练生成的图片
- 由于本人水平有限,难免出现错漏,敬请批评改正。
- 更多精彩内容,可点击进入人工智能知识点专栏、Python日常小操作专栏、OpenCV-Python小应用专栏、YOLO系列专栏、自然语言处理专栏或我的个人主页查看
- 基于DETR的人脸伪装检测
- YOLOv7训练自己的数据集(口罩检测)
- YOLOv8训练自己的数据集(足球检测)
- YOLOv5:TensorRT加速YOLOv5模型推理
- YOLOv5:IoU、GIoU、DIoU、CIoU、EIoU
- 玩转Jetson Nano(五):TensorRT加速YOLOv5目标检测
- YOLOv5:添加SE、CBAM、CoordAtt、ECA注意力机制
- YOLOv5:yolov5s.yaml配置文件解读、增加小目标检测层
- Python将COCO格式实例分割数据集转换为YOLO格式实例分割数据集
- YOLOv5:使用7.0版本训练自己的实例分割模型(车辆、行人、路标、车道线等实例分割)
- 使用Kaggle GPU资源免费体验Stable Diffusion开源项目