图像生成：Pytorch实现一个简单的对抗生成网络模型

前言
相关介绍
具体步骤
- 准备并读取数据集
- 定义生成器
- 定义判别器
- 定义损失函数
- 定义优化器
- 开始训练
- 完整代码
训练生成的图片

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

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 layersself.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 truthsvalid = 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 inputreal_imgs = Variable(imgs.type(Tensor))# -----------------#  Train Generator# -----------------optimizer_G.zero_grad()# Sample noise as generator inputz = Variable(Tensor(np.random.normal(0, 1, (imgs.shape[0], opt.latent_dim))))# Generate a batch of imagesgen_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) / 2d_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 mathimport torchvision.transforms as transforms
from torchvision.utils import save_imagefrom torch.utils.data import DataLoader
from torchvision import datasets
from torch.autograd import Variableimport torch.nn as nn
import torch.nn.functional as F
import torchos.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 Falseclass 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 layersself.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 imgclass 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 truthsvalid = 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 inputreal_imgs = Variable(imgs.type(Tensor))# -----------------#  Train Generator# -----------------optimizer_G.zero_grad()# Sample noise as generator inputz = Variable(Tensor(np.random.normal(0, 1, (imgs.shape[0], opt.latent_dim))))# Generate a batch of imagesgen_imgs = generator(z)# Loss measures generator's ability to fool the discriminatorg_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 samplesreal_loss = adversarial_loss(discriminator(real_imgs), valid)fake_loss = adversarial_loss(discriminator(gen_imgs.detach()), fake)d_loss = (real_loss + fake_loss) / 2d_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) + iif batches_done % opt.sample_interval == 0:save_image(gen_imgs.data[:25], "images/%d.png" % batches_done, nrow=5, normalize=True)

在这里插入图片描述

训练生成的图片

在这里插入图片描述

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