# Getting unexpected NotImplementedError when running model **URL:** \ **Category:** Uncategorized\ **Created:** [January 25, 2020, 6:40am UTC](https://discuss.pytorch.org/t/getting-unexpected-notimplementederror-when-running-model/67604 "2020-01-25T06:40:08Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![seankala](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/seankala/32/22144_2.png) [@seankala](https://discuss.pytorch.org/u/seankala)\ **Post date:** [January 25, 2020, 6:40am UTC](https://discuss.pytorch.org/t/getting-unexpected-notimplementederror-when-running-model/67604/1 "2020-01-25T06:40:08Z")
Hello. I’m currently working on debugging a model I wrote using PyTorch. When I first ran `output = model(data)` I got the error ```auto *** RuntimeError: Expected tensor for argument #1 'indices' to have scalar type Long; but got torch.cuda.DoubleTensor instead (while checking arguments for embedding) ``` No problem, I simply ran `output = model(data.long())`. Then I got a: ```auto *** RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _th_index_select ``` I wasn’t sure what the error message exactly meant, but I recalled that I hadn’t put my model on the GPU device. So I ran: ```auto model = model.to('cuda') output = model(data.long()) ``` but this time I got a: ```auto *** NotImplementedError ``` This was a bit unexpected, and I checked if I had put in a `NotImplementedError` anywhere in the code but I hadn’t. I’m having some difficulty finding helpful resources, as I don’t even know what the causing piece of code is. Would anybody have any idea how I should handle this issue? Just an FYI, these errors occurred while I was in the PDB interactive shell. Thanks in advance. ---
**Author:** ![G.M](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/g.m/32/19266_2.png) [@G.M](https://discuss.pytorch.org/u/G.M)\ **Post date:** [January 25, 2020, 6:56am UTC](https://discuss.pytorch.org/t/getting-unexpected-notimplementederror-when-running-model/67604/2 "2020-01-25T06:56:04Z")
1. The `.to()` method needs the device code of the device, for gpus, the code is usually something like “cuda:0”. You can also use `.cuda()`. 2. Idk what device is `data` on, but calling `.long()` only changes it to Long type on its original device. If ur model is on gpu, u also have to change the inputs to gpu. In this case, I guess `data` is not on gpu. ---
**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:** [January 25, 2020, 7:01am UTC](https://discuss.pytorch.org/t/getting-unexpected-notimplementederror-when-running-model/67604/3 "2020-01-25T07:01:26Z")
As an addition to what @G.M said, could you please print the complete stack trace you get from the `NotImplementedError`? You would get this error, e.g. if you have a typo in a method name (e.g. `forwrad` instead of `forward`) or if you use a wrong indentation. ---
**Author:** ![seankala](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/seankala/32/22144_2.png) [@seankala](https://discuss.pytorch.org/u/seankala)\ **Post date:** [January 25, 2020, 7:39am UTC](https://discuss.pytorch.org/t/getting-unexpected-notimplementederror-when-running-model/67604/4 "2020-01-25T07:39:57Z")
@G.M I’ve also put the `data` on GPU via `data.to('cuda')`. I’ve never had a problem from not specifying the device and just using `'cuda'`. Double checking right now `data` is a PyTorch tensor with `device='cuda:0'`. ---
**Author:** ![G.M](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/g.m/32/19266_2.png) [@G.M](https://discuss.pytorch.org/u/G.M)\ **Post date:** [January 25, 2020, 9:18am UTC](https://discuss.pytorch.org/t/getting-unexpected-notimplementederror-when-running-model/67604/5 "2020-01-25T09:18:54Z")
Then could u please print the whole stack trace as @ptrblck said ? ---
**Author:** ![seankala](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/seankala/32/22144_2.png) [@seankala](https://discuss.pytorch.org/u/seankala)\ **Post date:** [January 26, 2020, 7:55am UTC](https://discuss.pytorch.org/t/getting-unexpected-notimplementederror-when-running-model/67604/6 "2020-01-26T07:55:40Z")
Here’s the traceback that I’ve been able to get: ```auto Traceback (most recent call last): File "./main.py", line 27, in main() File "./main.py", line 20, in main output = model(data.long()) File "C:\Users\user1\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__ result = self.forward(*input, **kwargs) File "C:\Users\user1\Desktop\github\transformer_implementation\transformer.py", line 25, in forward enc_output = self.encoder(x) File "C:\Users\user1\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__ result = self.forward(*input, **kwargs) File "C:\Users\user1\Desktop\github\transformer_implementation\encoder.py", line 54, in forward output = self.encoder_stacked(x) File "C:\Users\user1\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__ result = self.forward(*input, **kwargs) File "C:\Users\user1\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 97, in forward raise NotImplementedError NotImplementedError ``` I didn’t initially include too many details here in the original post, but the `model` that I’m using has a `nn.ModuleList` inside of it. After going through parts of the code, I found out that this was the problem. More specifically, it looks like: ```auto self.encoder_stacked = nn.ModuleList([Encoder(self.config) for _ in range(self.N)]) ``` According to [this Stack Overflow question](https://stackoverflow.com/questions/52241680/pytorch-notimplementederror-in-forward) it seems that there are cases where the indentation may cause problems, but that’s not the case for me. The `Encoder` module looks like this: ```auto class Encoder(nn.Module): def __init__ (self, config, dropout=True): super(). __init__ () self.config = config self.d_model = self.config.d_model self.attention = MultiheadAttention(self.config) if dropout: self.dropout = nn.Dropout(p=self.config.dropout_rate) else: self.dropout = nn.Dropout(p=0.0) self.norm = Normalization(features=self.d_model) self.ffnn = FeedforwardNN(self.config) def forward(self, x): attn_output = self.attention(x, x, x) sublayer1_output = self.norm(x + attn_output) sublayer1_output = self.dropout(sublayer1_output) ffnn_output = self.ffnn(sublayer1_output) sublayer2_output = self.norm(sublayer1_output + ffnn_output) sublayer2_output = self.dropout(sublayer2_output) return sublayer2_output ``` ---
**Author:** ![seankala](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/seankala/32/22144_2.png) [@seankala](https://discuss.pytorch.org/u/seankala)\ **Post date:** [January 26, 2020, 8:43am UTC](https://discuss.pytorch.org/t/getting-unexpected-notimplementederror-when-running-model/67604/7 "2020-01-26T08:43:06Z")
I think I may have found a solution [here](https://discuss.pytorch.org/t/when-should-i-use-nn-modulelist-and-when-should-i-use-nn-sequential/5463/4). I’ll do some more research based off of this answer. ---
**Author:** ![G.M](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/g.m/32/19266_2.png) [@G.M](https://discuss.pytorch.org/u/G.M)\ **Post date:** [January 26, 2020, 10:36am UTC](https://discuss.pytorch.org/t/getting-unexpected-notimplementederror-when-running-model/67604/8 "2020-01-26T10:36:41Z")
Yes, ModuleList does not have a `forward` method. So u definitely can’t call on any ModuleList object as u did.