Pytorch Subclass of nn.Module has no attribute 'parameters'

Question

Python Version: Python 3.8.5
Pytorch Version: '1.6.0'

I am defining LSTM, a subclass of nn.Module. I am trying to create an optimizer but I am getting the following error: torch.nn.modules.module.ModuleAttributeError: 'LSTM' object has no attribute 'paramters'

I have two code files, train.py and lstm_class.py (contain the LSTM class). I will try to produce a minimum working example, let me know if any other information is helpful.

The code in lstm_class.py:

import torch.nn as nn

class LSTM(nn.Module):

    def __init__(self, vocab_size, embedding_dim, hidden_dim, n_layers, drop_prob=0.2):
        super(LSTM, self).__init__()

        # network size parameters
        self.n_layers = n_layers
        self.hidden_dim = hidden_dim
        self.vocab_size = vocab_size
        self.embedding_dim = embedding_dim


        # the layers of the network
        self.embedding = nn.Embedding(self.vocab_size, self.embedding_dim)
        self.lstm = nn.LSTM(self.embedding_dim, self.hidden_dim, self.n_layers, dropout=drop_prob, batch_first=True)
        self.dropout = nn.Dropout(drop_prob)
        self.fc = nn.Linear(self.hidden_dim, self.vocab_size)



    def forward(self, input, hidden):
        # Defines forward pass, probably isn't relevant

    def init_hidden(self, batch_size):
        #Initializes hidden state, probably isn't relevant

The code in train.py

import torch
import torch.optim
import torch.nn as nn
import lstm_class

vocab_size = 1000
embedding_dim = 256
hidden_dim = 256
n_layers = 2

net = lstm_class.LSTM(vocab_size, embedding_dim, hidden_dim, n_layers)
optimizer = torch.optim.Adam(net.paramters(), lr=learning_rate) 

I am getting the error on the last line written above. The full error message:

Traceback (most recent call last):
  File "train.py", line 58, in <module>
    optimizer = torch.optim.Adam(net.paramters(), lr=learning_rate)
  File "/usr/local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 771, in __getattr__
    raise ModuleAttributeError("'{}' object has no attribute '{}'".format(
torch.nn.modules.module.ModuleAttributeError: 'LSTM' object has no attribute 'paramters'

Any tips for how to fix this would be appreciated. Also as written above, let me know if anything else would be relevant. Thanks

Answer 1

It's not net.paramters(), it's net.parameters() :)