Coding-GAN-生成对抗网络-基于RGB图片数据

• 摘要
• gan.py

摘要

gan.py用于训练网络
图片数据放在/home/myself/work/work-generate/data/data下

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 Dataset,DataLoader
from torchvision import datasets
from torch.autograd import Variable

import torch.nn as nn
import torch.nn.functional as F
import torch
from torchvision.datasets import ImageFolder


from PIL import Image
import torchvision.models as models

# 加载预训练的VGG模型
vgg = models.vgg16(pretrained=True)
os.makedirs("/home/myself/work/work-generate/images", exist_ok=True)

parser = argparse.ArgumentParser()
parser.add_argument("--n_epochs", type=int, default=2000, help="number of epochs of training")
parser.add_argument("--batch_size", type=int, default=32, 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=1000, help="dimensionality of the latent space")
parser.add_argument("--img_size", type=int, default=128, help="size of each image dimension")
parser.add_argument("--channels", type=int, default=3, 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)


# 自定义数据集类
class CustomImageDataset(Dataset):
    def __init__(self, root_dir, transform=None):
        self.root_dir = root_dir
        self.transform = transform
        self.images = [f for f in os.listdir(root_dir) if f.endswith('.jpg')]

    def __len__(self):
        return len(self.images)

    def __getitem__(self, idx):
        img_path = os.path.join(self.root_dir, self.images[idx])
        image = Image.open(img_path).convert("RGB")  # 确保图片是RGB模式

        if self.transform:
            image = self.transform(image)

        return image

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


img_shape = (opt.channels, opt.img_size, opt.img_size)

cuda = True if torch.cuda.is_available() else False





# 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

# 图像预处理
transform = transforms.Compose([
    transforms.Resize((opt.img_size, opt.img_size)),  # 确保这与模型输入尺寸匹配
    transforms.ToTensor(),  # 将PIL Image转换为Tensor
    transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])  # 归一化
])

# 创建数据集实例
dataset = CustomImageDataset(root_dir='/home/myself/work/work-generate/data', transform=transform)

# 创建DataLoader实例
dataloader = DataLoader(
    dataset,
    batch_size=opt.batch_size,  # 使用您之前定义的批处理大小
    shuffle=True,  # 在每个epoch开始时打乱数据
    num_workers=opt.n_cpu,  # 使用指定数量的CPU线程加载数据
)


# 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




def main():
    

    # ----------
    #  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], "/home/myself/work/work-generate/images/%d.png" % batches_done, nrow=5, normalize=True)


if __name__ == '__main__':
    main()