1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
import argparse
import os
import numpy as np
import math
import sys

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

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
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=0.00005, help="learning rate")
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=64, help="size of each image dimension")
parser.add_argument("--channels", type=int, default=3, help="number of image channels")
parser.add_argument("--n_critic", type=int, default=5, help="number of training steps for discriminator per iter")
parser.add_argument("--clip_value", type=float, default=0.01, help="lower and upper clip value for disc. weights")
parser.add_argument("--sample_interval", type=int, default=400, help="interval betwen image samples")
opt = parser.parse_known_args()[0]
print(opt)

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

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

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
class Generator(nn.Module):
    def __init__(self):
        super(Generator, self).__init__()

        self.init_size = opt.img_size // 4
        # 第一层是为了把的噪声（batch_size, 100)
        # 拉到 (batch_size, 128, img_size, img_size)
        self.l1 = nn.Sequential(nn.Linear(opt.latent_dim, 128 * self.init_size ** 2))

        self.conv_blocks = nn.Sequential(
            nn.BatchNorm2d(128),
            nn.Upsample(scale_factor=2),
            nn.Conv2d(128, 128, 3, stride=1, padding=1),
            nn.BatchNorm2d(128, 0.8),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Upsample(scale_factor=2),
            nn.Conv2d(128, 64, 3, stride=1, padding=1),
            nn.BatchNorm2d(64, 0.8),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(64, opt.channels, 3, stride=1, padding=1),
            nn.Tanh(),
        )

    def forward(self, z):
        out = self.l1(z)
        out = out.view(out.shape[0], 128, self.init_size, self.init_size)
        img = self.conv_blocks(out)
        return img

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
# 这里相较于DCGAN没有使用交叉熵


# Initialize generator and discriminator
generator = Generator()
discriminator = Discriminator()

if cuda:
    generator.cuda()
    discriminator.cuda()

# Initialize weights
generator.apply(weights_init_normal)
discriminator.apply(weights_init_normal)

# Configure data loader
dataloader = torch.utils.data.DataLoader(
    datasets.ImageFolder(
        "data/",
        transform=transforms.Compose(
            [transforms.Resize(opt.img_size), transforms.ToTensor(), transforms.Normalize([0.5], [0.5])]
        ),
    ),
    batch_size=opt.batch_size,
    shuffle=True,
)

# Optimizers
# 这里相较于DCGAN，Adam优化器换成了RMSprop
optimizer_G = torch.optim.RMSprop(generator.parameters(), lr=opt.lr)
optimizer_D = torch.optim.RMSprop(discriminator.parameters(), lr=opt.lr)

Tensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
# ----------
#  Training
# ----------

for epoch in range(opt.n_epochs):
    for i, (imgs, _) in enumerate(dataloader):

        # Configure input
        real_imgs = Variable(imgs.type(Tensor))
        real_imgs = real_imgs.resize_(imgs.shape[0], opt.channels, opt.img_size,  opt.img_size)
        # ---------------------
        #  Train Discriminator
        # ---------------------
        
        # 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)

        optimizer_D.zero_grad()

        # Measure discriminator's ability to classify real from generated samples
        real_loss = discriminator(real_imgs)
        fake_loss = discriminator(gen_imgs.detach())
        # was距离是要最大化 real_loss - fake_loss
        # 这里加上一个符号，loss下降就相当于最大化was距离
        d_loss = torch.mean(-real_loss + fake_loss)

        d_loss.backward()
        optimizer_D.step()
        
        # Clip weights of discriminator
        for p in discriminator.parameters():
            p.data.clamp_(-opt.clip_value, opt.clip_value)

        # Train the generator every n_critic iterations
        if i % opt.n_critic == 0:
    
            # -----------------
            #  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 = torch.mean(-discriminator(gen_imgs))

            g_loss.backward()
            optimizer_G.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)