得到512个通道而不是64个-我应该在我的自动编码器中更改什么？
得到512个通道而不是64个-我应该在我的自动编码器中更改什么？
提问于 2020-03-04 03:32:57
ndf = 128
z_size = 512
# define the model (a simple autoencoder)
class MyNetwork(nn.Module):
def __init__(self):
super(MyNetwork, self).__init__()
self.encoder = nn.Sequential(
nn.Conv2d(3, 6, kernel_size=3, stride=1, padding=1),
nn.ReLU(True),
nn.Conv2d(6,16,kernel_size=3, stride=1, padding=1),
nn.ReLU(True),
nn.Conv2d(16,64,kernel_size=3, stride=1, padding=1),
nn.ReLU(True))
self.decoder = nn.Sequential(
nn.ConvTranspose2d(64,16,kernel_size=3, stride=1, padding=1),
nn.ReLU(True),
nn.ConvTranspose2d(16,6,kernel_size=3, stride=1, padding=1),
nn.ReLU(True),
nn.ConvTranspose2d(6,3,kernel_size=3, stride=1, padding=1),
nn.ReLU(True))
self.fc1 = nn.Linear(ndf*4*8*16,z_size)
self.fc2 = nn.Linear(ndf*4*8*16,z_size)
self.d1 = nn.Linear(z_size, ndf*4*8*8)
self.z_size = z_size
self.d_max = ndf *4
def encode(self, x):
x = self.encoder(x)
x = x.view(x.shape[0], -1)
mu = self.fc1(x)
log_var = self.fc2(x)
return mu, log_var
def decode(self,x):
x = x.view(x.shape[0], self.z_size)
x = self.d1(x)
x = x.view(x.shape[0], self.d_max, 8,8)
x = self.decoder(x)
return x
def reparameterize(self, mu, log_var):
std = torch.exp(0.5 * log_var)
eps = torch.randn_like(std)
return eps.mul(std).add_(mu)
def forward(self, x):
mu, log_var = self.encode(x)
mu = mu.squeeze()
log_var = log_var.squeeze()
z = self.reparameterize(mu, log_var)
return self.decode(z.view(-1, self.z_size, 1, 1)), mu, log_var我改编了一个教程中的代码，当我尝试运行我的自动编码器时，我得到了错误‘给定transposed=1，权重为64 16 33，预期input16,512，8，8有64个通道，但得到512个通道’。
有人可以解释一下，我应该如何使用CIFAR10数据集进一步调整这段代码，批处理大小为16。
回答 2
Stack Overflow用户
发布于 2020-03-04 13:53:46
浏览您的代码，发现输入和输出维度不正确。
假设输入和输出数组的形状都是32x32x3，我格式化了这段代码。
ndf = 128
z_size = 512
# define the model (a simple autoencoder)
class MyNetwork(nn.Module):
def __init__(self):
super(MyNetwork, self).__init__()
self.encoder = nn.Sequential(
nn.Conv2d(3, 6, kernel_size=3, stride=1, padding=1),
nn.ReLU(True),
nn.Conv2d(6,16,kernel_size=3, stride=1, padding=1),
nn.ReLU(True),
nn.Conv2d(16,64,kernel_size=3, stride=1, padding=1),
nn.ReLU(True))
self.decoder = nn.Sequential(
nn.ConvTranspose2d(64,16,kernel_size=3, stride=1, padding=1),
nn.ReLU(True),
nn.ConvTranspose2d(16,6,kernel_size=3, stride=1, padding=1),
nn.ReLU(True),
nn.ConvTranspose2d(6,3,kernel_size=3, stride=1, padding=1),
nn.ReLU(True))
self.fc1 = nn.Linear(ndf*4*8*16,z_size)
self.fc2 = nn.Linear(ndf*4*8*16,z_size)
self.d1 = nn.Linear(z_size, ndf*4*8*16)
self.z_size = z_size
self.d_max = ndf *4
def encode(self, x):
x = self.encoder(x)
x = x.view(x.shape[0], -1)
mu = self.fc1(x)
log_var = self.fc2(x)
return mu, log_var
def decode(self,x):
x = x.view(x.shape[0], self.z_size)
x = self.d1(x)
x = x.view(x.shape[0], 64, 32, 32)
x = self.decoder(x)
return x
def reparameterize(self, mu, log_var):
std = torch.exp(0.5 * log_var)
eps = torch.randn_like(std)
return eps.mul(std).add_(mu)
def forward(self, x):
mu, log_var = self.encode(x)
mu = mu.squeeze()
log_var = log_var.squeeze()
z = self.reparameterize(mu, log_var)
return self.decode(z.view(-1, self.z_size, 1, 1)), mu, log_var希望这段代码能正常工作:)
Stack Overflow用户
发布于 2020-03-04 14:00:20
decoder ( forward函数中的x = self.decoder(x))的输入应具有64个通道，如nn.ConvTranspose2d(64,16,kernel_size=3, stride=1, padding=1)所定义。
为此，您可以执行以下更改：
在x = x.view(x.shape[0], 64, 32, 32)的self.d1 = nn.Linear(z_size, ndf*4*8*16).
- Change方法中，
- 将
self.d1 = nn.Linear(z_size, ndf*4*8*8)从x = x.view(x.shape[0], self.d_max, 8,8)更改为decoder
使用print语句分析不同层的输入张量的形状：
ndf = 128
z_size = 512
# define the model (a simple autoencoder)
class MyNetwork(nn.Module):
def __init__(self):
super(MyNetwork, self).__init__()
self.encoder = nn.Sequential(
nn.Conv2d(3, 6, kernel_size=3, stride=1, padding=1),
nn.ReLU(True),
nn.Conv2d(6,16,kernel_size=3, stride=1, padding=1),
nn.ReLU(True),
nn.Conv2d(16,64,kernel_size=3, stride=1, padding=1),
nn.ReLU(True))
self.decoder = nn.Sequential(
nn.ConvTranspose2d(64,16,kernel_size=3, stride=1, padding=1),
nn.ReLU(True),
nn.ConvTranspose2d(16,6,kernel_size=3, stride=1, padding=1),
nn.ReLU(True),
nn.ConvTranspose2d(6,3,kernel_size=3, stride=1, padding=1),
nn.ReLU(True))
self.fc1 = nn.Linear(ndf*4*8*16,z_size)
self.fc2 = nn.Linear(ndf*4*8*16,z_size)
self.d1 = nn.Linear(z_size, ndf*4*8*16)
self.z_size = z_size
self.d_max = ndf *4
def encode(self, x):
print('encoder')
print(x.shape)
x = self.encoder(x)
print(x.shape)
x = x.view(x.shape[0], -1)
print(x.shape)
mu = self.fc1(x)
print(mu.shape)
log_var = self.fc2(x)
print(log_var.shape)
return mu, log_var
def decode(self,x):
print('decoder')
print(x.shape)
x = x.view(x.shape[0], self.z_size)
print(x.shape)
x = self.d1(x)
print(x.shape)
x = x.view(x.shape[0], 64, 32, 32)
print(x.shape)
x = self.decoder(x)
print(x.shape)
return x
def reparameterize(self, mu, log_var):
std = torch.exp(0.5 * log_var)
eps = torch.randn_like(std)
return eps.mul(std).add_(mu)
def forward(self, x):
mu, log_var = self.encode(x)
mu = mu.squeeze()
log_var = log_var.squeeze()
z = self.reparameterize(mu, log_var)
return self.decode(z.view(-1, self.z_size, 1, 1)), mu, log_var页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/60514292
复制相关文章
相似问题
腾讯云开发者
