[英]Pytorch + Residual Network throws unexpected: TypeError: 'NoneType' object is not callable
I am diving into the world of Deep Learning and as Python is my most prominent programming language I decided to start with the Pytorch framework.我正在深入学习深度学习的世界,由于 Python 是我最杰出的编程语言,我决定从 Pytorch 框架开始。 Following a tutorial I implemented a ResNet of 50 layers.
按照教程,我实现了一个 50 层的 ResNet。 Afterwards I tried to make an ResNet-18 with simpler blocks which looked like this:
之后,我尝试用更简单的块制作 ResNet-18,如下所示:
class baseBlock(torch.nn.Module):
expansion = 1
def __init__(self,input_planes,planes,stride=1,dim_change=None):
super(baseBlock,self).__init__()
#Declare convolutional layers with batch norms
self.conv1 = torch.nn.Conv2d(input_planes, planes, stride=stride, kernel_size=3, padding=1)
self.bn1 = torch.nn.BatchNorm2d(planes)
self.conv2 = torch.nn.Conv2d(planes, planes, stride=1, kernel_size=3, padding=1)
self.bn2 = torch.nn.BatchNorm2d(planes)
self.dim_change = dim_change
def forward(self,x):
#Save the residue
res = x
output = F.relu(self.bn1(self.conv1(x)))
output = self.bn2(self.conv2(output))
if self.dim_change is not None:
res = self.dim_change(res)
output += res
output = F.relu(output)
return output
I divided the code into the blocks and the actual Neural Network to make it more understandable.我将代码分成块和实际的神经网络,以使其更易于理解。 The rest of the code for the NN is:
NN 的代码 rest 为:
class ResNet(torch.nn.Module):
def __init__(self,block,num_layers,classes=10):
super(ResNet,self).__init__()
#according to research paper
self.input_planes = 64
self.conv1 = torch.nn.Conv2d(3,64,kernel_size =3,stride=1,padding=1)
self.bn1 = torch.nn.BatchNorm2d(64)
self.layer1 = self._layer(block, 64, num_layers[0], stride=1)
self.layer2 = self._layer(block, 128, num_layers[1], stride=2)
self.layer3 = self._layer(block, 256, num_layers[2], stride=2)
self.layer4 = self._layer(block, 512, num_layers[3], stride=2)
self.avaragePool = torch.nn.AvgPool2d(kernel_size=4,stride=1)
self.fc = torch.nn.Linear(512*block.expansion, classes)
def _layer(self,block,planes,num_layers,stride=1):
dim_change = None
if stride != 1 or planes != self.input_planes*block.expansion:
dim_change = torch.nn.Sequential(torch.nn.Conv2d(self.input_planes, planes*block.expansion, kernel_size = 1, stride=stride),
torch.nn.BatchNorm2d(planes*block.expansion))
netLayers = []
netLayers.append(block(self.input_planes,planes,stride=stride, dim_change=dim_change))
self.input_planes = planes*block.expansion
for i in range(1,num_layers):
netLayers.append(block(self.input_planes,planes))
self.input_planes = planes * block.expansion
return torch.nn.Sequential(*netLayers)
def forward(self,x):
x = F.relu(self.bn1(self.conv1(x)))
#Problem at this layer
x = self.layer1(x) <- NoneType object is not callable
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = F.avg_pool2d(x,4)
x = x.view(x.size(0),-1)
x = self.fc(x)
return x
The problem arises on the last forward function in the layer1 that is marked on the code.问题出现在代码上标记的layer1中的最后一个转发function。 If I comment it the network keeps on computing (obviously it throws an error later because the dimensions are not right but it still does something).
如果我评论它,网络会继续计算(显然它稍后会引发错误,因为尺寸不正确但它仍然会做一些事情)。 If I change the stride on this first layer the problem also resolves but still throws an error later for the same dimensional reasons.
如果我在第一层更改步幅,问题也会解决,但由于相同的维度原因,稍后仍会引发错误。 I don't seem to figure out what the problem is.
我似乎没有弄清楚问题是什么。 I use a standard CIFAR10 dataset to train it and the training code is as standard as it gets.
我使用标准的 CIFAR10 数据集对其进行训练,并且训练代码尽可能标准。
If I can provided any additional information let me know.如果我可以提供任何其他信息,请告诉我。 Thank you
谢谢
This is a simple typo.这是一个简单的错字。 Your
return
is inside the if
, and the only layer with stride==1
is the layer1
:您的
return
在if
内,并且stride==1
的唯一层是layer1
:
def _layer(self,block,planes,num_layers,stride=1):
dim_change = None
if stride != 1 or planes != self.input_planes*block.expansion:
# [...]
return torch.nn.Sequential(*netLayers)
Therefore, for the layer1
, there is no return
, hence None
.因此,对于
layer1
,没有return
,因此None
。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.