gan.py

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=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=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)  #打标签，真图为1
        fake = Variable(Tensor(imgs.size(0), 1).fill_(0.0), requires_grad=False)   #假图为0

        # Configure input
        real_imgs = Variable(imgs.type(Tensor))

        # -----------------
        #  Train Generator
        # -----------------

        #另外Pytorch 为什么每一轮batch需要设置optimizer.zero_grad：
        #根据pytorch中的backward()函数的计算，当网络参量进行反馈时，梯度是被积累的而不是被替换掉；但是在每一个batch时毫无疑问并不需要将两个batch的梯度混合起来累积，因此这里就需要每个batch设置一遍zero_grad 了。
        optimizer_G.zero_grad()

        # Sample noise as generator input
        z = Variable(Tensor(np.random.normal(0, 1, (imgs.shape[0], opt.latent_dim)))) #加入随机噪声

        # Generate a batch of images
        gen_imgs = generator(z) # 根据噪声生成虚假样本

        # Loss measures generator's ability to fool the discriminator
        g_loss = adversarial_loss(discriminator(gen_imgs), valid)# 用真实的标签+假样本，计算生成器损失


        g_loss.backward() # 生成器梯度反向传播，反向传播经过了判别器，故此时判别器参数也有梯度
        optimizer_G.step()# 生成器参数更新，判别器参数虽然有梯度，但是这一步不能更新判别器

        #那么为什么optimizer.step()需要放在每一个batch训练中，而不是epoch训练中，
        # 这是因为现在的mini-batch训练模式是假定每一个训练集就只有mini-batch这样大，
        # 因此实际上可以将每一次mini-batch看做是一次训练，一次训练更新一次参数空间，因而optimizer.step()放在这里。

        # ---------------------
        #  Train Discriminator
        # ---------------------

        optimizer_D.zero_grad()# 把生成器损失函数梯度反向传播时，顺带计算的判别器参数梯度清空

        # Measure discriminator's ability to classify real from generated samples
        real_loss = adversarial_loss(discriminator(real_imgs), valid)# 真样本+真标签：判别器损失
        # 在判别器前向传播过程，输入的假数据被 detach 。这个数据和生成它的计算图“脱钩”了，即梯度传到它那个地方就停了
        fake_loss = adversarial_loss(discriminator(gen_imgs.detach()), fake)# 假样本+假标签：判别器损失
        d_loss = (real_loss + fake_loss) / 2# 判别器总的损失函数

        d_loss.backward()# 判别器损失回传
        optimizer_D.step()# 判别器参数更新



        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)