用GAN生成奖杯

数据集链接：https://pan.baidu.com/s/19Uxc2ELiMG3acUtLeSTDTA?pwd=wsyw
提取码：wsyw

我设置的图片大小为128*128，如果内存爆炸可以将batch_size调小，epoch我设置的2000，我感觉其实1000也够了。代码如下：

import argparse
from torchvision import datasets, transforms
import torch
import torch.nn as nn
import os
import numpy as np
from torchvision.utils import save_image


def args_parse():
    parser = argparse.ArgumentParser()
    parser.add_argument("--n_epoches", type=int, default=2000, help="number of epochs of training")
    parser.add_argument("--batch_size", type=int, default=256, help="size of the batches")
    parser.add_argument("--lr", type=float, default=0.0002, help="adam: learning rate")
    parser.add_argument("--n_cpu", type=int, default=1, 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=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=50, help="interval between image sampling")
    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("--type", type=str, default='DCGAN', help="The type of DCGAN")
    return parser.parse_args()

class Generator(nn.Module):
    def __init__(self, latent_dim, img_shape):
        super(Generator, self).__init__()
        self.img_shape = img_shape
        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(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), self.img_shape[0], self.img_shape[1], self.img_shape[2])
        return img


class Discriminator(nn.Module):
    def __init__(self, img_shape):
        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


class Generator_CNN(nn.Module):
    def __init__(self, latent_dim, img_shape):
        super(Generator_CNN, self).__init__()
        self.init_size = img_shape[1] // 4
        self.l1 = nn.Sequential(nn.Linear(latent_dim, 128 * self.init_size ** 2))  # 100 ——> 128 * 8 * 8 = 8192
        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, img_shape[0], 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


class Discriminator_CNN(nn.Module):
    def __init__(self, img_shape):
        super(Discriminator_CNN, self).__init__()
        def discriminator_block(in_filters, out_filters, bn=True):
            block = [nn.Conv2d(in_filters, out_filters, 3, 2, 1),
                     nn.LeakyReLU(0.2, inplace=True),
                     nn.Dropout2d(0.25)]
            if bn:
                block.append(nn.BatchNorm2d(out_filters, 0.8))
            return block
        self.model = nn.Sequential(
            *discriminator_block(img_shape[0], 16, bn=False),
            *discriminator_block(16, 32),
            *discriminator_block(32, 64),
            *discriminator_block(64, 128),
        )
        ds_size = img_shape[1] // 2 ** 4
        self.adv_layer = nn.Sequential(nn.Linear(128 * ds_size ** 2, 1), nn.Sigmoid())  # 128 * 2 * 2 ——> 1

    def forward(self, img):
        out = self.model(img)
        out = out.view(out.shape[0], -1)
        # print('out:', out.shape)
        validity = self.adv_layer(out)
        return validity


def train():
    opt = args_parse()
    transform = transforms.Compose(
        [
            transforms.Resize((128, 128)),
            transforms.ToTensor(),
            transforms.Normalize([0.5], [0.5])
        ])
    data = datasets.ImageFolder('./dataset', transform=transform)
    train_loader = torch.utils.data.DataLoader(
        data,
        batch_size=opt.batch_size,
        shuffle=True)
    img_shape = (opt.channels, opt.img_size, opt.img_size)
    # Construct generator and discriminator
    if opt.type == 'DCGAN':
        generator = Generator_CNN(opt.latent_dim, img_shape)
        discriminator = Discriminator_CNN(img_shape)
    else:
        generator = Generator(opt.latent_dim, img_shape)
        discriminator = Discriminator(img_shape)
    adversarial_loss = torch.nn.BCELoss()
    cuda = True if torch.cuda.is_available() else False
    if cuda:
        generator.cuda()
        discriminator.cuda()
        adversarial_loss.cuda()
    # Optimizers
    optimizer_G = torch.optim.Adam(generator.parameters(), lr=(opt.lr * 8 / 9), 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
    for epoch in range(opt.n_epoches):
        for i, (imgs, _) in enumerate(train_loader):
            # adversarial ground truths
            valid = torch.ones(imgs.shape[0], 1).type(Tensor)
            fake = torch.zeros(imgs.shape[0], 1).type(Tensor)
            real_imgs = imgs.type(Tensor)
            #############    Train Generator    ################
            optimizer_G.zero_grad()
            # sample noise as generator input
            z = torch.tensor(np.random.normal(0, 1, (imgs.shape[0], opt.latent_dim))).type(Tensor)
            # Generate a batch of images
            gen_imgs = generator(z)
            # G-Loss
            g_loss = adversarial_loss(discriminator(gen_imgs), valid)
            g_loss.backward()
            optimizer_G.step()
            #############  Train Discriminator ################
            optimizer_D.zero_grad()
            # D-Loss
            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_epoches, i, len(train_loader), d_loss.item(), g_loss.item())
            )
            batches_done = epoch * len(train_loader) + i
            os.makedirs("images_3_2", exist_ok=True)
            if batches_done % opt.sample_interval == 0:
                save_image(gen_imgs.data[:25], "images_3_2/%d.png" % (batches_done), nrow=5, normalize=True)


if __name__ == '__main__':
    train()
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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185

实验效果如下：