GAN学习笔记（一）项目链接
GAN学习笔记（一）项目链接
- 1、开源项目
- 2、GAN 组成
-
- 2.1 来自生成mnist的gan
- 2.2 来自cyclegan
- 2.3 参考上面的Discriminator，准备自己写一个3D的版本
1、开源项目
看到这个里面整理了好多gan的项目。
https://github.com/eriklindernoren/PyTorch-GAN
2、GAN 组成
GAN由2各部分组成，分别是Generator和Discriminator，即生成器和判别器。
生成器的目的是以假乱真。
判别器的目的是辨别假对象。
2.1 来自生成mnist的gan
输入二值图像尺寸28*28.
class Generator(nn.Module):
def __init__(self):
super(Generator, self).__init__()
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(opt.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), *img_shape)
return img
class Discriminator(nn.Module):
def __init__(self):
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
2.2 来自cyclegan
输入彩色图像尺寸256*256.
##############################
# RESNET
##############################
class ResidualBlock(nn.Module):
def __init__(self, in_features):
super(ResidualBlock, self).__init__()
self.block = nn.Sequential(
nn.ReflectionPad2d(1),
nn.Conv2d(in_features, in_features, 3),
nn.InstanceNorm2d(in_features),
nn.ReLU(inplace=True),
nn.ReflectionPad2d(1),
nn.Conv2d(in_features, in_features, 3),
nn.InstanceNorm2d(in_features),
)
def forward(self, x):
return x + self.block(x)
class GeneratorResNet(nn.Module):
def __init__(self, input_shape, num_residual_blocks):
super(GeneratorResNet, self).__init__()
channels = input_shape[0]
# Initial convolution block
out_features = 64
model = [
nn.ReflectionPad2d(channels),
nn.Conv2d(channels, out_features, 7),
nn.InstanceNorm2d(out_features),
nn.ReLU(inplace=True),
]
in_features = out_features
# Downsampling
for _ in range(2):
out_features *= 2
model += [
nn.Conv2d(in_features, out_features, 3, stride=2, padding=1),
nn.InstanceNorm2d(out_features),
nn.ReLU(inplace=True),
]
in_features = out_features
# Residual blocks
for _ in range(num_residual_blocks):
model += [ResidualBlock(out_features)]
# Upsampling
for _ in range(2):
out_features //= 2
model += [
nn.Upsample(scale_factor=2),
nn.Conv2d(in_features, out_features, 3, stride=1, padding=1),
nn.InstanceNorm2d(out_features),
nn.ReLU(inplace=True),
]
in_features = out_features
# Output layer
model += [nn.ReflectionPad2d(channels), nn.Conv2d(out_features, channels, 7), nn.Tanh()]
self.model = nn.Sequential(*model)
def forward(self, x):
return self.model(x)
##############################
# Discriminator
##############################
class Discriminator(nn.Module):
def __init__(self, input_shape):
super(Discriminator, self).__init__()
channels, height, width = input_shape
# Calculate output shape of image discriminator (PatchGAN)
self.output_shape = (1, height // 2 ** 4, width // 2 ** 4)
def discriminator_block(in_filters, out_filters, normalize=True):
"""Returns downsampling layers of each discriminator block"""
layers = [nn.Conv2d(in_filters, out_filters, 4, stride=2, padding=1)]
if normalize:
layers.append(nn.InstanceNorm2d(out_filters))
layers.append(nn.LeakyReLU(0.2, inplace=True))
return layers
self.model = nn.Sequential(
*discriminator_block(channels, 64, normalize=False),
*discriminator_block(64, 128),
*discriminator_block(128, 256),
*discriminator_block(256, 512),
nn.ZeroPad2d((1, 0, 1, 0)),
nn.Conv2d(512, 1, 4, padding=1)
)
def forward(self, img):
return self.model(img)
判别器尺寸变化： 256 → 128 → 64 → 32 → 16 → 17 → 16 256 \rightarrow 128\rightarrow 64\rightarrow 32\rightarrow 16\rightarrow 17\rightarrow 16 256→128→64→32→16→17→16
2.3 参考上面的Discriminator，准备自己写一个3D的版本
比如输入尺寸是192192256，参考cyclegan那里，使用patchgan。对于2维图像，输入维度是4，即（N,C,H,W），对于3维图像，输入维度是5,即（N,C,D,H,W）。
下面代码暂时还没有修改，改成3D后尺寸变化：
( 192 ∗ 192 ∗ 256 ) → ( 96 ∗ 96 ∗ 128 ) → ( 48 ∗ 48 ∗ 64 ) → ( 24 ∗ 24 ∗ 32 ) → ( 12 ∗ 12 ∗ 16 ) → ( 13 ∗ 13 ∗ 17 ) → ( 12 ∗ 12 ∗ 16 ) (192*192*256) \rightarrow (96*96*128)\rightarrow (48*48*64)\rightarrow (24*24*32)\rightarrow (12*12*16)\rightarrow (13*13*17)\rightarrow (12*12*16) (192∗192∗256)→(96∗96∗128)→(48∗48∗64)→(24∗24∗32)→(12∗12∗16)→(13∗13∗17)→(12∗12∗16)
##############################
# Discriminator
##############################
class Discriminator(nn.Module):
def __init__(self, input_shape):
super(Discriminator, self).__init__()
channels, height, width = input_shape
# Calculate output shape of image discriminator (PatchGAN)
self.output_shape = (1, height // 2 ** 4, width // 2 ** 4)
def discriminator_block(in_filters, out_filters, normalize=True):
"""Returns downsampling layers of each discriminator block"""
layers = [nn.Conv2d(in_filters, out_filters, 4, stride=2, padding=1)]
if normalize:
layers.append(nn.InstanceNorm2d(out_filters))
layers.append(nn.LeakyReLU(0.2, inplace=True))
return layers
self.model = nn.Sequential(
*discriminator_block(channels, 64, normalize=False),
*discriminator_block(64, 128),
*discriminator_block(128, 256),
*discriminator_block(256, 512),
nn.ZeroPad2d((1, 0, 1, 0)),
nn.Conv2d(512, 1, 4, padding=1)
)
def forward(self, img):
return self.model(img)