0. 工程实现

原理解析：
论文解析：GAN：Generative Adversarial Nets

1. GAN对抗生成网络结构

2. GAN 构造损失函数（LOSS）

LOSS公式与含义：

LOSS代码实现：

import torch
from torch import autograd
input = autograd.Variable(torch.tensor([[ 1.9072,  1.1079,  1.4906],[-0.6584, -0.0512,  0.7608],[-0.0614,  0.6583,  0.1095]]), requires_grad=True)
print(input)
print('-'*100)from torch import nn
m = nn.Sigmoid()
print(m(input))
print('-'*100)target = torch.FloatTensor([[0, 1, 1], [1, 1, 1], [0, 0, 0]])
print(target)
print('-'*100)import mathr11 = 0 * math.log(0.8707) + (1-0) * math.log((1 - 0.8707))
r12 = 1 * math.log(0.7517) + (1-1) * math.log((1 - 0.7517))
r13 = 1 * math.log(0.8162) + (1-1) * math.log((1 - 0.8162))r21 = 1 * math.log(0.3411) + (1-1) * math.log((1 - 0.3411))
r22 = 1 * math.log(0.4872) + (1-1) * math.log((1 - 0.4872))
r23 = 1 * math.log(0.6815) + (1-1) * math.log((1 - 0.6815))r31 = 0 * math.log(0.4847) + (1-0) * math.log((1 - 0.4847))
r32 = 0 * math.log(0.6589) + (1-0) * math.log((1 - 0.6589))
r33 = 0 * math.log(0.5273) + (1-0) * math.log((1 - 0.5273))r1 = -(r11 + r12 + r13) / 3
#0.8447112733378236
r2 = -(r21 + r22 + r23) / 3
#0.7260397266631787
r3 = -(r31 + r32 + r33) / 3
#0.8292933181294807
bceloss = (r1 + r2 + r3) / 3 
print(bceloss)
print('-'*100)loss = nn.BCELoss()
print(loss(m(input), target))
print('-'*100)loss = nn.BCEWithLogitsLoss()
print(loss(input, target))

loss BCEloss代码逐行运行结果

3. GAN对抗生成网络核心逻辑

整个简单的gan网络代码由以下三个部分组成：

3.1 参数加载：

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 False

3.2 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

3.3 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# 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)