/
dcgan_folder.py
262 lines (223 loc) · 8.98 KB
/
dcgan_folder.py
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
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
import argparse
import os
import random
import torch
from torch import nn
from torch import optim
from torch.backends import cudnn as cudnn
from torchvision import datasets as dset
from torchvision import transforms as transforms
from torchvision import utils as vutils
parser = argparse.ArgumentParser()
parser.add_argument('--dataset', required=True, help='lsun | imagenet | folder | lfw | fake')
parser.add_argument('--dataroot', required=True, help='path to dataset')
parser.add_argument('--workers', type=int, help='number of data loading workers', default=2)
parser.add_argument('--batchSize', type=int, default=64, help='inputs batch size')
parser.add_argument('--imageSize', type=int, default=64, help='the height / width of the inputs image to network')
parser.add_argument('--nz', type=int, default=100, help='size of the latent z vector')
parser.add_argument('--ngf', type=int, default=64)
parser.add_argument('--ndf', type=int, default=64)
parser.add_argument('--niter', type=int, default=50, help='number of epochs to train for')
parser.add_argument('--lr', type=float, default=0.0002, help='learning rate, default=0.0002')
parser.add_argument('--beta1', type=float, default=0.5, help='beta1 for adam. default=0.5')
parser.add_argument('--cuda', action='store_true', help='enables cuda')
parser.add_argument('--ngpu', type=int, default=1, help='number of GPUs to use')
parser.add_argument('--netG', default='', help="path to netG (to continue training)")
parser.add_argument('--netD', default='', help="path to netD (to continue training)")
parser.add_argument('--outf', default='.', help='folder to output images and model checkpoints')
parser.add_argument('--manualSeed', type=int, help='manual seed')
parser.add_argument('--model', type=str, default='train', help='GAN train models.default: \'train\'. other: gen')
opt = parser.parse_args()
print(opt)
try:
os.makedirs(opt.outf)
except OSError:
pass
if opt.manualSeed is None:
opt.manualSeed = random.randint(1, 10000)
print("Random Seed: ", opt.manualSeed)
random.seed(opt.manualSeed)
torch.manual_seed(opt.manualSeed)
cudnn.benchmark = True
if torch.cuda.is_available() and not opt.cuda:
print("WARNING: You have a CUDA device, so you should probably run with --cuda")
if opt.dataset in ['imagenet', 'folder', 'lfw']:
# folder dataset
dataset = dset.ImageFolder(root=opt.dataroot,
transform=transforms.Compose([
transforms.Resize(opt.imageSize),
transforms.CenterCrop(opt.imageSize),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
]))
elif opt.dataset == 'lsun':
dataset = dset.LSUN(root=opt.dataroot, classes=['bedroom_train'],
transform=transforms.Compose([
transforms.Resize(opt.imageSize),
transforms.CenterCrop(opt.imageSize),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
]))
elif opt.dataset == 'fake':
dataset = dset.FakeData(image_size=(3, opt.imageSize, opt.imageSize),
transform=transforms.ToTensor())
assert dataset
dataloader = torch.utils.data.DataLoader(dataset, batch_size=opt.batchSize,
shuffle=True, num_workers=int(opt.workers))
device = torch.device("cuda:0" if opt.cuda else "cpu")
ngpu = int(opt.ngpu)
nz = int(opt.nz)
ngf = int(opt.ngf)
ndf = int(opt.ndf)
nc = 3
# custom weights initialization called on netG and netD
def weights_init_normal(m):
classname = m.__class__.__name__
if classname.find("Conv") != -1:
torch.nn.init.normal_(m.weight.data, 0.0, 0.02)
elif classname.find("BatchNorm") != -1:
torch.nn.init.normal_(m.weight.data, 1.0, 0.02)
torch.nn.init.constant_(m.bias.data, 0.0)
class Generator(nn.Module):
def __init__(self, gpus):
super(Generator, self).__init__()
self.ngpu = gpus
self.main = nn.Sequential(
# inputs is Z, going into a convolution
nn.ConvTranspose2d(nz, ngf * 8, 4, 1, 0, bias=False),
nn.BatchNorm2d(ngf * 8),
nn.ReLU(True),
# state size. (ngf*8) x 4 x 4
nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),
nn.BatchNorm2d(ngf * 4),
nn.ReLU(True),
# state size. (ngf*4) x 8 x 8
nn.ConvTranspose2d(ngf * 4, ngf * 2, 4, 2, 1, bias=False),
nn.BatchNorm2d(ngf * 2),
nn.ReLU(True),
# state size. (ngf*2) x 16 x 16
nn.ConvTranspose2d(ngf * 2, ngf, 4, 2, 1, bias=False),
nn.BatchNorm2d(ngf),
nn.ReLU(True),
# state size. (ngf) x 32 x 32
nn.ConvTranspose2d(ngf, nc, 4, 2, 1, bias=False),
nn.Tanh()
# state size. (nc) x 64 x 64
)
def forward(self, inputs):
if inputs.is_cuda and self.ngpu > 1:
outputs = nn.parallel.data_parallel(self.main, inputs, range(self.ngpu))
else:
outputs = self.main(inputs)
return outputs
netG = Generator(ngpu).to(device)
netG.apply(weights_init_normal)
if opt.netG != '':
if torch.cuda.is_available():
netG = torch.load(opt.netG)
else:
netG = torch.load(opt.netG, map_location='cpu')
class Discriminator(nn.Module):
def __init__(self, gpus):
super(Discriminator, self).__init__()
self.ngpu = gpus
self.main = nn.Sequential(
# inputs is (nc) x 64 x 64
nn.Conv2d(nc, ndf, 4, 2, 1, bias=False),
nn.LeakyReLU(0.2, inplace=True),
# state size. (ndf) x 32 x 32
nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),
nn.BatchNorm2d(ndf * 2),
nn.LeakyReLU(0.2, inplace=True),
# state size. (ndf*2) x 16 x 16
nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),
nn.BatchNorm2d(ndf * 4),
nn.LeakyReLU(0.2, inplace=True),
# state size. (ndf*4) x 8 x 8
nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),
nn.BatchNorm2d(ndf * 8),
nn.LeakyReLU(0.2, inplace=True),
# state size. (ndf*8) x 4 x 4
nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),
nn.Sigmoid()
)
def forward(self, inputs):
if inputs.is_cuda and self.ngpu > 1:
outputs = nn.parallel.data_parallel(self.main, inputs, range(self.ngpu))
else:
outputs = self.main(inputs)
return outputs.view(-1, 1).squeeze(1)
netD = Discriminator(ngpu).to(device)
netD.apply(weights_init_normal)
if opt.netD != '':
if torch.cuda.is_available():
netD = torch.load(opt.netD)
else:
netD = torch.load(opt.netD, map_location='cpu')
criterion = nn.BCELoss()
# setup optimizer
optimizerD = optim.Adam(netD.parameters(), lr=opt.lr, betas=(opt.beta1, 0.999))
optimizerG = optim.Adam(netG.parameters(), lr=opt.lr, betas=(opt.beta1, 0.999))
def gen_sample():
data = torch.utils.data.DataLoader(dataset, num_workers=int(opt.workers))
for i, (imgs, _) in enumerate(data):
noise = torch.randn(imgs.size(0), nz, 1, 1)
vutils.save_image(netG(noise).detach(),
f'{opt.outf}/{i}.png',
normalize=True)
def train():
for epoch in range(opt.niter):
for i, (data, _) in enumerate(dataloader):
############################
# (1) Update D network: maximize log(D(x)) + log(1 - D(G(z)))
###########################
# train with real
netD.zero_grad()
img = data.to(device)
batch_size = img.size(0)
label = torch.full((batch_size,), 1, device=device)
output = netD(img)
errD_real = criterion(output, label)
errD_real.backward()
D_x = output.mean().item()
# train with fake
noise = torch.randn(batch_size, nz, 1, 1, device=device)
fake = netG(noise)
label.fill_(0)
output = netD(fake.detach())
errD_fake = criterion(output, label)
errD_fake.backward()
D_G_z1 = output.mean().item()
errD = errD_real + errD_fake
optimizerD.step()
############################
# (2) Update G network: maximize log(D(G(z)))
###########################
netG.zero_grad()
label.fill_(1) # fake labels are real for generator cost
output = netD(fake)
errG = criterion(output, label)
errG.backward()
D_G_z2 = output.mean().item()
optimizerG.step()
print(f'[{epoch + 1}/{opt.niter}][{i}/{len(dataloader)}] '
f'Loss_D: {errD:.4f} '
f'Loss_G: {errG:.4f} '
f'D(x): {D_x:.4f} '
f'D(G(z)): {D_G_z1:.4f} / {D_G_z2:.4f}')
if i % 100 == 0:
vutils.save_image(data,
f'{opt.outf}/real_samples.png',
normalize=True)
fake = netG(noise)
vutils.save_image(fake.detach(),
f'{opt.outf}/fake_samples_epoch_{epoch + 1}.png',
normalize=True)
# do checkpointing
torch.save(netG, f'{opt.outf}/netG_epoch_{epoch + 1}.pth')
torch.save(netD, f'{opt.outf}/netD_epoch_{epoch + 1}.pth')
if __name__ == '__main__':
if opt.model == 'train':
train()
elif opt.model == 'gen':
gen_sample()