pix2pix网络，Pytorch代码中， valid 和 fake 两个参数表示啥

Posted 2023-05-02

valid = Variable(Tensor(np.ones((real_A.size(0), *patch))), requires_grad=False)
fake = Variable(Tensor(np.zeros((real_A.size(0), *patch))), requires_grad=False)

这两句是什么意思

参考技术A class UNetDown(nn.Module):
def __init__(self, in_size, out_size, normalize=True, dropout=0.0):
super(UNetDown, self).__init__()
layers = [nn.Conv2d(in_size, out_size, 4, 2, 1, bias=False)]
if normalize:
layers.append(nn.InstanceNorm2d(out_size))
layers.append(nn.LeakyReLU(0.2))
if dropout:
layers.append(nn.Dropout(dropout))
self.model = nn.Sequential(*layers)

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

class UNetUp(nn.Module):
def __init__(self, in_size, out_size, dropout=0.0):
super(UNetUp, self).__init__()
layers = [ nn.ConvTranspose2d(in_size, out_size, 4, 2, 1, bias=False),
nn.InstanceNorm2d(out_size),
nn.ReLU(inplace=True)]
if dropout:
layers.append(nn.Dropout(dropout))

self.model = nn.Sequential(*layers)

def forward(self, x, skip_input):
x = self.model(x)
x = torch.cat((x, skip_input), 1)

return x

class GeneratorUNet(nn.Module):
def __init__(self, in_channels=3, out_channels=3):
super(GeneratorUNet, self).__init__()

self.down1 = UNetDown(in_channels, 64, normalize=False)
self.down2 = UNetDown(64, 128)
self.down3 = UNetDown(128, 256)
self.down4 = UNetDown(256, 512, dropout=0.5)
self.down5 = UNetDown(512, 512, dropout=0.5)
self.down6 = UNetDown(512, 512, dropout=0.5)
self.down7 = UNetDown(512, 512, dropout=0.5)
self.down8 = UNetDown(512, 512, normalize=False, dropout=0.5)

self.up1 = UNetUp(512, 512, dropout=0.5)
self.up2 = UNetUp(1024, 512, dropout=0.5)
self.up3 = UNetUp(1024, 512, dropout=0.5)
self.up4 = UNetUp(1024, 512, dropout=0.5)
self.up5 = UNetUp(1024, 256)
self.up6 = UNetUp(512, 128)
self.up7 = UNetUp(256, 64)

self.final = nn.Sequential(
nn.Upsample(scale_factor=2),
nn.ZeroPad2d((1, 0, 1, 0)),
nn.Conv2d(128, out_channels, 4, padding=1),
nn.Tanh()
)

def forward(self, x):
# U-Net generator with skip connections from encoder to decoder
d1 = self.down1(x)
d2 = self.down2(d1)
d3 = self.down3(d2)
d4 = self.down4(d3)
d5 = self.down5(d4)
d6 = self.down6(d5)
d7 = self.down7(d6)
d8 = self.down8(d7)
u1 = self.up1(d8, d7)
u2 = self.up2(u1, d6)
u3 = self.up3(u2, d5)
u4 = self.up4(u3, d4)
u5 = self.up5(u4, d3)
u6 = self.up6(u5, d2)
u7 = self.up7(u6, d1)

return self.final(u7)
---------------------追问

您好，pix2pix网络结构我看懂了，多谢。
我想问的是，在计算目标函数时，valid 和 fake 这两个参数是什么意思

参考技术B 判别器的真假标签

如何在 Pytorch 中编写以下 Keras 神经网络的等效代码？

【中文标题】如何在 Pytorch 中编写以下 Keras 神经网络的等效代码？

【英文标题】：How can I write the below equivalent code of Keras Neural Net in Pytorch?

【发布时间】：2019-06-05 03:31:08

【问题描述】：

actor = Sequential()
        actor.add(Dense(20, input_dim=9, activation='relu', kernel_initializer='he_uniform'))
        actor.add(Dense(20, activation='relu'))
        actor.add(Dense(27, activation='softmax', kernel_initializer='he_uniform'))
        actor.summary()
        # See note regarding crossentropy in cartpole_reinforce.py
        actor.compile(loss='categorical_crossentropy',
                      optimizer=Adam(lr=self.actor_lr))[Please find the image eq here.][1]


  [1]: https://i.stack.imgur.com/gJviP.png

【问题讨论】：

到目前为止你有什么尝试？

【参考方案1】：

类似的问题已经被问过，但这里是这样的：

import torch

actor = torch.nn.Sequential(
    torch.nn.Linear(9, 20), # output shape has to be specified
    torch.nn.ReLU(),
    torch.nn.Linear(20, 20), # same goes over here
    torch.nn.ReLU(),
    torch.nn.Linear(20, 27), # and here
    torch.nn.Softmax(),
)

print(actor)

初始化：默认情况下，从 1.0 版本开始，线性层将使用 Kaiming Uniform 进行初始化（参见this post）。如果您想以不同的方式初始化权重，请参阅this question 的最受好评的回答。

您也可以使用 Python 的 OrderedDict 来更轻松地匹配某些层，请参阅 Pytorch's documentation，您应该可以从那里继续。