GANs/utils.py at main · sscott108/GANs · GitHub

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
#!/usr/bin/env python
# coding: utf-8

# In[ ]:


import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.datasets as datasets
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
from tqdm import tqdm
from torch.utils.tensorboard import SummaryWriter
import matplotlib.pyplot as plt

class Discriminator(nn.Module):
    def __init__(self, channels_img, features_d):
        super(Discriminator, self).__init__()
        self.disc = nn.Sequential(
            # input: N x channels_img x 64 x 64
            nn.Conv2d(
                channels_img, features_d, kernel_size=4, stride=2, padding=1
            ),
            nn.LeakyReLU(0.2),
            # _block(in_channels, out_channels, kernel_size, stride, padding)
            self._block(features_d, features_d * 2, 4, 2, 1),
            self._block(features_d * 2, features_d * 4, 4, 2, 1),
            self._block(features_d * 4, features_d * 8, 4, 2, 1),
            # After all _block img output is 4x4 (Conv2d below makes into 1x1)
            nn.Conv2d(features_d * 8, 1, kernel_size=4, stride=2, padding=0),
        )

    def _block(self, in_channels, out_channels, kernel_size, stride, padding):
        return nn.Sequential(
            nn.Conv2d(
                in_channels,
                out_channels,
                kernel_size,
                stride,
                padding,
                bias=False,
            ),
            nn.InstanceNorm2d(out_channels, affine=True),
            nn.LeakyReLU(0.2),
        )

    def forward(self, x):
        return self.disc(x)


class Generator(nn.Module):
    def __init__(self, channels_noise, channels_img, features_g):
        super(Generator, self).__init__()
        self.net = nn.Sequential(
            # Input: N x channels_noise x 1 x 1
            self._block(channels_noise, features_g * 16, 4, 1, 0),  # img: 4x4
            self._block(features_g * 16, features_g * 8, 4, 2, 1),  # img: 8x8
            self._block(features_g * 8, features_g * 4, 4, 2, 1),  # img: 16x16
            self._block(features_g * 4, features_g * 2, 4, 2, 1),  # img: 32x32
            nn.ConvTranspose2d(
                features_g * 2, channels_img, kernel_size=4, stride=2, padding=1
            ),
            # Output: N x channels_img x 64 x 64
            nn.Tanh(),
        )

    def _block(self, in_channels, out_channels, kernel_size, stride, padding):
        return nn.Sequential(
            nn.ConvTranspose2d(
                in_channels,
                out_channels,
                kernel_size,
                stride,
                padding,
                bias=False,
            ),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(),
        )

    def forward(self, x):
        return self.net(x)


def initialize_weights(model):
    # Initializes weights according to the DCGAN paper
    for m in model.modules():
        if isinstance(m, (nn.Conv2d, nn.ConvTranspose2d, nn.BatchNorm2d)):
            nn.init.normal_(m.weight.data, 0.0, 0.02)


def gradient_penalty(critic, real, fake, device = 'cpu'):
    batch_size, c, h, w = real.shape
    epsilon = torch.rand((batch_size, 1, 1, 1)).repeat(1,c,h,w).to(device)
    interpolated_images = real*epsilon + (1-epsilon)*fake


    #calculate critic scores
    mixed_scores=critic(interpolated_images)
    gradient = torch.autograd.grad(
        inputs=interpolated_images,
        outputs=mixed_scores,
        grad_outputs = torch.ones_like(mixed_scores),
        create_graph = True,
        retain_graph = True,
    )[0]
    gradient= gradient.view(gradient.shape[0], -1)
    gradient_norm = gradient.norm(2, dim=1)

    gradient_penalty = torch.mean((gradient_norm -1)**2)
    return gradient_penalty