# AttributeError: 'Sequential' object has no attribute 'weight' **URL:** \ **Category:** Uncategorized\ **Created:** [August 20, 2019, 5:10pm UTC](https://discuss.pytorch.org/t/attributeerror-sequential-object-has-no-attribute-weight/53855 "2019-08-20T17:10:12Z")\ **Posts on this page:** 10\ **Page:** 1
**Author:** ![ammalikwaterloo](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/74df32/32.png) [@ammalikwaterloo](https://discuss.pytorch.org/u/ammalikwaterloo)\ **Post date:** [August 20, 2019, 5:10pm UTC](https://discuss.pytorch.org/t/attributeerror-sequential-object-has-no-attribute-weight/53855/1 "2019-08-20T17:10:12Z")
Hello, I am using a model from > However when I use print(“weight[0,0] b4 average: %f” % model.classifier.weight[0,0].item()) I got the error. Thanks, ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [August 20, 2019, 5:32pm UTC](https://discuss.pytorch.org/t/attributeerror-sequential-object-has-no-attribute-weight/53855/2 "2019-08-20T17:32:53Z")
`model.classifier` is defines as `nn.Sequential`, so you would have to index the module inside it, e.g. ```python model.classifier[0].weight ``` ---
**Author:** ![TO\_Kocsis](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/t/58f4c7/32.png) [@TO\_Kocsis](https://discuss.pytorch.org/u/TO_Kocsis)\ **Post date:** [January 4, 2020, 12:00pm UTC](https://discuss.pytorch.org/t/attributeerror-sequential-object-has-no-attribute-weight/53855/3 "2020-01-04T12:00:38Z")
Using: > #load > pretrained\_dict = torch.load(‘H:/workspace/pretrain/epoch\_500\_pretrain\_resnet50.pth’) > model\_dict = model.state\_dict() > # 1. filter out unnecessary keys > pretrained\_dict = {k: v for k, v in pretrained\_dict.items() if k in model\_dict} > # 2. overwrite entries in the existing state dict > model\_dict.update(pretrained\_dict) > # 3. load the new state dict > model.load\_state\_dict(model\_dict) > # copy braches 0 → branches 1/2 > model.branches[1].weight.copy\_(model.branches[0].weight) I get an error: AttributeError: ‘Sequential’ object has no attribute ‘weight’ Im not sure whats wrong? Here is an image of the model structure that might reveal the issue? ![image](https://discuss.pytorch.org/uploads/default/original/3X/1/6/164e395f6e2e3c415bbb6ceaf93acac744688e04.png) ---
**Author:** ![Eta\_C](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/eta_c/32/17667_2.png) [@Eta\_C](https://discuss.pytorch.org/u/Eta_C)\ **Post date:** [January 4, 2020, 12:09pm UTC](https://discuss.pytorch.org/t/attributeerror-sequential-object-has-no-attribute-weight/53855/4 "2020-01-04T12:09:50Z")
It seems that this module is **a Sequential of Sequentials** , try ```python model.branches[0][1].weight ``` ---
**Author:** ![TO\_Kocsis](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/t/58f4c7/32.png) [@TO\_Kocsis](https://discuss.pytorch.org/u/TO_Kocsis)\ **Post date:** [January 4, 2020, 1:49pm UTC](https://discuss.pytorch.org/t/attributeerror-sequential-object-has-no-attribute-weight/53855/5 "2020-01-04T13:49:28Z")
> model.branches[0][1].weight.copy\_(model.branches[0][0].weight) AttributeError: ‘AdaptiveAvgPool2d’ object has no attribute ‘weight’ ![image](https://discuss.pytorch.org/uploads/default/original/3X/8/b/8b5e59edbca5b82bceacda1e484299b0f679aef6.png) If I understand correctly, this adresses as follows: model → \_modules:branches → \_modules: 0 → \_modules:1 = AAP2d I tried to track down where the weights are in debugging: ![image](https://discuss.pytorch.org/uploads/default/original/3X/6/5/65da576aa7e05471cb8ff141a1ef75258cb2b227.png) But I still cant find how to address it correctly, when to use the number indexing, or the . indexing? I tried for example: > model.branches[1][0].conv1.weight .copy\_( model.branches[0][0].conv1.weight ) AttributeError: ‘Sequential’ object has no attribute ‘conv1’ ---
**Author:** ![Eta\_C](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/eta_c/32/17667_2.png) [@Eta\_C](https://discuss.pytorch.org/u/Eta_C)\ **Post date:** [January 5, 2020, 6:09am UTC](https://discuss.pytorch.org/t/attributeerror-sequential-object-has-no-attribute-weight/53855/6 "2020-01-05T06:09:28Z")
> [@TO\_Kocsis](#): > > But I still cant find how to address it correctly, when to use the number indexing, or the . indexing? > I tried for example: You don’t understand the key points. - Use number indexing for `Sequential` and `ModuleList` - Use key for `ModuleDict` - Use .module\_name otherwise For example, if I have a network like ```python import torch.nn as nn class SubNet(nn.Module): def __init__ (self): super(). __init__ () self.conv = nn.Conv2d(2, 2, 2) self.relu = nn.ReLU(inplace=True) def forward(self, x): return x class Net(nn.Module): def __init__ (self): super(). __init__ () self.module = nn.Sequential( nn.Sequential( nn.Conv2d(1, 1, 1), SubNet(), ), nn.Conv2d(3, 3, 3) ) self.conv = nn.Conv2d(4, 4, 4) def forward(self, x): return x net = Net() print(net) ``` The output is ```auto Net( (module): Sequential( (0): Sequential( (0): Conv2d(1, 1, kernel_size=(1, 1), stride=(1, 1)) (1): SubNet( (conv): Conv2d(2, 2, kernel_size=(2, 2), stride=(1, 1)) (relu): ReLU(inplace=True) ) ) (1): Conv2d(3, 3, kernel_size=(3, 3), stride=(1, 1)) ) (conv): Conv2d(4, 4, kernel_size=(4, 4), stride=(1, 1)) ) ``` Then we have `net.module[0][0].weight` → `Conv2d(1, 1, 1)`'s weight `net.module[0][1].conv.weight` → `Conv2d(2, 2, 2)`'s weight `net.module[1].weight` → `Conv2d(3, 3, 3)`'s weight `net.conv.weight` → `Conv2d(4, 4, 4)`'s weight ---
**Author:** ![TO\_Kocsis](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/t/58f4c7/32.png) [@TO\_Kocsis](https://discuss.pytorch.org/u/TO_Kocsis)\ **Post date:** [January 6, 2020, 11:36am UTC](https://discuss.pytorch.org/t/attributeerror-sequential-object-has-no-attribute-weight/53855/7 "2020-01-06T11:36:42Z")
Thanks you example was very informative. I had problems understanding and seeing clearly from pycharm debug, but printing the net makes it much more clear. ---
**Author:** ![Kamil\_Adamczewski](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/kamil_adamczewski/32/12077_2.png) [@Kamil\_Adamczewski](https://discuss.pytorch.org/u/Kamil_Adamczewski)\ **Post date:** [April 2, 2020, 3:41pm UTC](https://discuss.pytorch.org/t/attributeerror-sequential-object-has-no-attribute-weight/53855/8 "2020-04-02T15:41:48Z")
What would we do without you. ---
**Author:** ![Fathima](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/f/f6c823/32.png) [@Fathima](https://discuss.pytorch.org/u/Fathima)\ **Post date:** [July 5, 2022, 8:37am UTC](https://discuss.pytorch.org/t/attributeerror-sequential-object-has-no-attribute-weight/53855/9 "2022-07-05T08:37:15Z")
I am trying to initialise the weight but I get this error and I followed the thread but I don’t understand how I could fix in my code. I have 2 con layers and 2 fc layers this is my architecture ```auto #original code class ConvNet(nn.Module): def __init__ (self): super(ConvNet, self). __init__ () #refer the article ... self.conv1 = nn.Sequential( nn.Conv1d(1, 32, kernel_size=2, stride=1), nn.Dropout(0.5), nn.ReLU()) self.conv2 = nn.Sequential( nn.Conv1d(32,32, kernel_size=2, stride=1), nn.Dropout(0.5), nn.ReLU(), nn.MaxPool1d(2,stride=3)) self.conv3 = nn.Sequential( nn.Conv1d(32, 32, kernel_size=2, stride=1), nn.Dropout(0.5), nn.ReLU()) #fully connected layers self.fc1 = nn.Linear(32*47,32) #self.fc2 = nn.Linear(32,1) self.fc2 = nn.Linear(32,1) #self.activation = nn.Softmax() #self.activation = nn.Sigmoid() # Initialization nn.init.zeros_(self.conv1.weight) nn.init.zeros_(self.conv2.bias) def forward(self, x): # input x : #expected conv1d input = minibatch_size * num_channel * width batch_size=x.size(0) y = self.conv1(x.view(batch_size,1,-1)) y = self.conv2(y) y = self.conv3(y) #print(y.size()) batch_size= y.size(0) y = y.flatten(start_dim=1) #print(y.size()) y = self.fc1(y.view(y.size(0), -1)) #y = self.fc1(y.view(batch_size,1,-1)) y = self.fc2(y.view(batch_size,1,-1)) return y ``` ```auto ``` ````auto AttributeError Traceback (most recent call last) in 1 #check the output size ----> 2 Model = ConvNet() 3 X = (torch.randn(32, 1, 145)) 4 output=Model(X) 5 #print(output.size()) in __init__ (self) 30 31 # Initialization ---> 32 nn.init.zeros_(self.conv1.weight) 33 nn.init.zeros_(self.conv2.bias) 34 ~\anaconda3\lib\site-packages\torch\nn\modules\module.py in __getattr__ (self, name) 1183 if name in modules: 1184 return modules[name] -> 1185 raise AttributeError("'{}' object has no attribute '{}'".format( 1186 type(self). __name__ , name)) 1187 AttributeError: 'Sequential' object has no attribute 'weight'``` ```` ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [July 5, 2022, 8:39am UTC](https://discuss.pytorch.org/t/attributeerror-sequential-object-has-no-attribute-weight/53855/10 "2022-07-05T08:39:03Z")
This line of code: ```python nn.init.zeros_(self.conv1.weight) ``` won’t work, since `self.conv1` is an `nn.Sequential` block and thus does not have any parameters. You would need to index the actual conv layer via `self.conv1[0]` and it should work: ```python nn.init.zeros_(self.conv1[0].weight) ```