Creating a RNN model for text generation
At PyBooks, you've been tasked to develop an algorithm that can perform text generation. The project involves auto-completion of book names. To kickstart this project, you decide to experiment with a Recurrent Neural Network (RNN). This way, you can understand the nuances of RNNs before moving to more complex models.
The following has been imported for you: torch
, torch.nn
as nn
.
The data
variable has been initialized with an excerpt from Alice's Adventures in Wonderland by Lewis Carroll.
This exercise is part of the course
Deep Learning for Text with PyTorch
Exercise instructions
- Include an RNN layer and linear layer in
RNNmodel
class - Instantiate the RNN model with input size as length of
chars
, hidden size of 16, and output size as length ofchars
.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Include an RNN layer and linear layer in RNNmodel class
class RNNmodel(nn.Module):
def __init__(self, input_size, hidden_size, output_size):
super(RNNmodel, self).__init__()
self.hidden_size = hidden_size
self.rnn = nn.____(input_size, hidden_size, batch_first=True)
self.fc = nn.____(hidden_size, output_size)
def forward(self, x):
h0 = torch.zeros(1, x.size(0), self.hidden_size)
out, _ = self.rnn(x, h0)
out = self.fc(out[:, -1, :])
return out
# Instantiate the RNN model
model = RNNmodel(____, ____, ____)