文章目录
前言
AN 的基本理念其实非常简单，其核心由两个目标互相冲突的神经网络组成，这两个网络会以越来越复杂的方法来“蒙骗”对方。这种情况可以理解为博弈论中的极大极小博弈树。以下就是传入马的网络生成斑马。
1、网络搭建
#!/usr/bin/env python
# coding: utf-8
import torch
import torch.nn as nn
class ResNetBlock(nn.Module): # <1>
def __init__(self, dim):
super(ResNetBlock, self).__init__()
self.conv_block = self.build_conv_block(dim)
def build_conv_block(self, dim):
conv_block = []
conv_block += [nn.ReflectionPad2d(1)]
conv_block += [nn.Conv2d(dim, dim, kernel_size=3, padding=0, bias=True),
nn.InstanceNorm2d(dim),
nn.ReLU(True)]
conv_block += [nn.ReflectionPad2d(1)]
conv_block += [nn.Conv2d(dim, dim, kernel_size=3, padding=0, bias=True),
nn.InstanceNorm2d(dim)]
return nn.Sequential(*conv_block)
def forward(self, x):
out = x + self.conv_block(x) # <2>
return out
class ResNetGenerator(nn.Module):
def __init__(self, input_nc=3, output_nc=3, ngf=64, n_blocks=9): # <3>
assert(n_blocks >= 0)
super(ResNetGenerator, self).__init__()
self.input_nc = input_nc
self.output_nc = output_nc
self.ngf = ngf
model = [nn.ReflectionPad2d(3),
nn.Conv2d(input_nc, ngf, kernel_size=7, padding=0, bias=True),
nn.InstanceNorm2d(ngf),
nn.ReLU(True)]
n_downsampling = 2
for i in range(n_downsampling):
mult = 2**i
model += [nn.Conv2d(ngf * mult, ngf * mult * 2, kernel_size=3,
stride=2, padding=1, bias=True),
nn.InstanceNorm2d(ngf * mult * 2),
nn.ReLU(True)]
mult = 2**n_downsampling
for i in range(n_blocks):
model += [ResNetBlock(ngf * mult)]
for i in range(n_downsampling):
mult = 2**(n_downsampling - i)
model += [nn.ConvTranspose2d(ngf * mult, int(ngf * mult / 2),
kernel_size=3, stride=2,
padding=1, output_padding=1,
bias=True),
nn.InstanceNorm2d(int(ngf * mult / 2)),
nn.ReLU(True)]
model += [nn.ReflectionPad2d(3)]
model += [nn.Conv2d(ngf, output_nc, kernel_size=7, padding=0)]
model += [nn.Tanh()]
self.model = nn.Sequential(*model)
def forward(self, input): # <3>
return self.model(input)
2、网络架构
ResNetGenerator(
(model): Sequential(
(0): ReflectionPad2d((3, 3, 3, 3))
(1): Conv2d(3, 64, kernel_size=(7, 7), stride=(1, 1))
(2): InstanceNorm2d(64, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(5): InstanceNorm2d(128, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(6): ReLU(inplace=True)
(7): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(8): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(9): ReLU(inplace=True
)
(10): ResNetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(11): ResNetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(12): ResNetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(13): ResNetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(14): ResNetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(15): ResNetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(16): ResNetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(17): ResNetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(18): ResNetBlock(
(conv_block): Sequential(
(0): ReflectionPad2d((1, 1, 1, 1))
(1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(2): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(3): ReLU(inplace=True)
(4): ReflectionPad2d((1, 1, 1, 1))
(5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
(6): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
)
)
(19): ConvTranspose2d(256, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(20): InstanceNorm2d(128, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(21): ReLU(inplace=True)
(22): ConvTranspose2d(128, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
(23): InstanceNorm2d(64, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
(24): ReLU(inplace=True)
(25): ReflectionPad2d((3, 3, 3, 3))
(26): Conv2d(64, 3, kernel_size=(7, 7), stride=(1, 1))
(27): Tanh()
)
)
3、网络架构解析
4、网络实例化
# 网络实例化
netG = ResNetGenerator()
5、网络权重加载
#
model_path = '../data/p1ch2/horse2zebra_0.4.0.pth'
model_data = torch.load(model_path)
netG.load_state_dict(model_data)
6、网络属性设置
#
netG.eval()
7、图像tensor化
#
from PIL import Image
from torchvision import transforms
#
preprocess = transforms.Compose([transforms.Resize(256),
transforms.ToTensor()])
8、导入测试图
#
img = Image.open('C:/Users/Administrator/Documents/horse.jpg')
9、图像tensor化
#
img_t = preprocess(img)
batch_t = torch.unsqueeze(img_t, 0)
10、图像传入网络
#
batch_out = netG(batch_t)
11、生成对抗图
#
out_t = (batch_out.data.squeeze() + 1.0) / 2.0
out_img = transforms.ToPILImage()(out_t)
out_img.save('../data/p1ch2/zebra.jpg')
out_img
12、对抗图解析
没有进行全连接，只是对像素点进行的计算
(25): ReflectionPad2d((3, 3, 3, 3))
(26): Conv2d(64, 3, kernel_size=(7, 7), stride=(1, 1))
(27): Tanh()