Python TypeError:hook()接受3个位置参数,但给出了4个
我正在尝试使用前向钩子从PyTorch中的ResNet18中间版本中提取特征Python TypeError:hook()接受3个位置参数,但给出了4个,python,pytorch,Python,Pytorch,我正在尝试使用前向钩子从PyTorch中的ResNet18中间版本中提取特征 class CCLModel(nn.Module): def __init__(self,output_layer,*args): self.output_layer = output_layer super().__init__(*args) self.output_layer = output_layer #PRETRAINED MODEL
class CCLModel(nn.Module):
def __init__(self,output_layer,*args):
self.output_layer = output_layer
super().__init__(*args)
self.output_layer = output_layer
#PRETRAINED MODEL
self.pretrained = models.resnet18(pretrained=True)
#TAKING OUTPUT FROM AN INTERMEDIATE LAYER
#self._layers = []
for l in list(self.pretrained._modules.keys()):
#self._layers.append(l)
if l == self.output_layer:
handle = getattr(self.pretrained,l).register_forward_hook(self.hook)
def hook(self,input,output):
return output
def _forward_impl(self, x):
x = self.pretrained(x)
return x
def forward(self, x):
return self._forward_impl(x)
我还希望预测与第4层的特征输出一起出现
但是我得到了TypeError:hook()接受了3个位置参数,但给出了4个
完整的错误消息如下
TypeError Traceback (most recent call last)
<ipython-input-66-18c4a0f917f2> in <module>()
----> 1 out = model(x.to('cuda:0').float())
6 frames
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
<ipython-input-61-71fe0d1420a6> in forward(self, x)
78
79 def forward(self, x):
---> 80 return self._forward_impl(x)
81
82 '''def forward(self,x):
<ipython-input-61-71fe0d1420a6> in _forward_impl(self, x)
73 #x = torch.flatten(x, 1)
74 #x = self.fc(x)
---> 75 x = self.pretrained(x)
76
77 return x
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
/usr/local/lib/python3.6/dist-packages/torchvision/models/resnet.py in forward(self, x)
218
219 def forward(self, x):
--> 220 return self._forward_impl(x)
221
222
/usr/local/lib/python3.6/dist-packages/torchvision/models/resnet.py in _forward_impl(self, x)
209 x = self.layer2(x)
210 x = self.layer3(x)
--> 211 x = self.layer4(x)
212
213 x = self.avgpool(x)
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
729 _global_forward_hooks.values(),
730 self._forward_hooks.values()):
--> 731 hook_result = hook(self, input, result)
732 if hook_result is not None:
733 result = hook_result
TypeError: hook() takes 3 positional arguments but 4 were given
TypeError回溯(最近一次调用)
在()
---->1 out=model(x.to('cuda:0').float())
6帧
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in_call_impl(self,*input,**kwargs)
725结果=self.\u slow\u forward(*输入,**kwargs)
726其他:
-->727结果=自转发(*输入,**kwargs)
728用于itertools.chain中的挂钩(
729 _全局_向前_hooks.values(),
前进中(自我,x)
78
79 def前进档(自身,x):
--->80返回自前向执行(x)
81
82''def前进(自身,x):
输入前向输入(self,x)
73#x=火炬。展平(x,1)
74#x=self.fc(x)
--->75 x=自预训练(x)
76
77返回x
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in_call_impl(self,*input,**kwargs)
725结果=self.\u slow\u forward(*输入,**kwargs)
726其他:
-->727结果=自转发(*输入,**kwargs)
728用于itertools.chain中的挂钩(
729 _全局_向前_hooks.values(),
/前进中的usr/local/lib/python3.6/dist-packages/torchvision/models/resnet.py(self,x)
218
219 def前进档(自身,x):
-->220返回自向前执行(x)
221
222
/usr/local/lib/python3.6/dist-packages/torchvision/models/resnet.py in\u forward\u impl(self,x)
209 x=自分层2(x)
210 x=自身。第3层(x)
-->211 x=自分层4(x)
212
213 x=self.avgpool(x)
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in_call_impl(self,*input,**kwargs)
729 _全局_向前_hooks.values(),
730自身.\u向前_hooks.values()):
-->731钩子结果=钩子(自身、输入、结果)
732如果hook_结果不是None:
733结果=挂钩结果
TypeError:hook()接受3个位置参数,但给出了4个
为什么钩子不起作用,尽管在各种论坛上我都看到了这样做的方法?这里是一个简单的前钩子示例,它必须有三个参数
model
,input
和output
:
m = models.resnet18(pretrained=False)
def hook(module, input, output):
print(output.detach().shape)
m.fc.register_forward_hook(hook)
尝试使用虚拟数据:
>>> m(torch.rand(1, 3, 224, 224))
torch.Size([1, 1000])
<<< tensor(...)
注-self
对应于CCLModel
实例,而model
是我们连接的层,即nn.Linear
下面是一个例子:
>>> m = CCLModel(nn.Linear(1000, 100))
>>> m(torch.rand(1, 3, 224, 224))
torch.Size([1, 100])
<<< tensor(...)
>m=CCL模型(nn.线性(1000100))
>>>m(火炬兰特(1,3,224,224))
火炬尺寸([1100])
>>> m = CCLModel(nn.Linear(1000, 100))
>>> m(torch.rand(1, 3, 224, 224))
torch.Size([1, 100])
<<< tensor(...)