Module models.rnn
Reccurent Neural Network for Shakespeare Dataset
Expand source code
#!/usr/bin/env python3
"""
Reccurent Neural Network for Shakespeare Dataset
"""
# Import PyTorch root package import torch
import torch
import torch.nn as nn
class RNN(nn.Module):
def __init__(self, vocab_size=90, embedding_dim=8, hidden_dim=512, num_layers=2):
super(RNN, self).__init__()
# set class variables
self.hidden_dim = hidden_dim
self.vocab_size = vocab_size
# embedding and LSTM layers
self.embedding = nn.Embedding(vocab_size, embedding_dim)
self.num_lstm_layers = num_layers
self.lstm = nn.LSTM(embedding_dim, hidden_dim, batch_first=True, num_layers=num_layers)
# linear and sigmoid layers
self.fc = nn.Linear(hidden_dim, vocab_size)
def forward(self, input, hidden):
embeds = self.embedding(input)
lstm_out, hidden = self.lstm1(embeds, hidden)
out = self.fc(lstm_out)
# flatten the output
out = out.reshape(-1, self.vocab_size)
return out, hidden
def init_hidden(self, batch_size, device):
hidden = (torch.zeros(self.num_lstm_layers, batch_size, self.hidden_dim).to(device = device),
torch.zeros(self.num_lstm_layers, batch_size, self.hidden_dim).to(device = device))
return hidden
# TODO: Any way we can actually have an useful pretrained argument here?
def rnn(pretrained=False, num_classes=90):
return RNN(vocab_size=num_classes)
def minirnn(pretrained=False, num_classes=90):
return RNN(vocab_size=num_classes, hidden_dim=128)
Functions
def minirnn(pretrained=False, num_classes=90)
-
Expand source code
def minirnn(pretrained=False, num_classes=90): return RNN(vocab_size=num_classes, hidden_dim=128)
def rnn(pretrained=False, num_classes=90)
-
Expand source code
def rnn(pretrained=False, num_classes=90): return RNN(vocab_size=num_classes)
Classes
class RNN (vocab_size=90, embedding_dim=8, hidden_dim=512, num_layers=2)
-
Base class for all neural network modules.
Your models should also subclass this class.
Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::
import torch.nn as nn import torch.nn.functional as F class Model(nn.Module): def __init__(self): super(Model, self).__init__() self.conv1 = nn.Conv2d(1, 20, 5) self.conv2 = nn.Conv2d(20, 20, 5) def forward(self, x): x = F.relu(self.conv1(x)) return F.relu(self.conv2(x))
Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:
to
, etc.:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool
Initializes internal Module state, shared by both nn.Module and ScriptModule.
Expand source code
class RNN(nn.Module): def __init__(self, vocab_size=90, embedding_dim=8, hidden_dim=512, num_layers=2): super(RNN, self).__init__() # set class variables self.hidden_dim = hidden_dim self.vocab_size = vocab_size # embedding and LSTM layers self.embedding = nn.Embedding(vocab_size, embedding_dim) self.num_lstm_layers = num_layers self.lstm = nn.LSTM(embedding_dim, hidden_dim, batch_first=True, num_layers=num_layers) # linear and sigmoid layers self.fc = nn.Linear(hidden_dim, vocab_size) def forward(self, input, hidden): embeds = self.embedding(input) lstm_out, hidden = self.lstm1(embeds, hidden) out = self.fc(lstm_out) # flatten the output out = out.reshape(-1, self.vocab_size) return out, hidden def init_hidden(self, batch_size, device): hidden = (torch.zeros(self.num_lstm_layers, batch_size, self.hidden_dim).to(device = device), torch.zeros(self.num_lstm_layers, batch_size, self.hidden_dim).to(device = device)) return hidden
Ancestors
- torch.nn.modules.module.Module
Class variables
var dump_patches : bool
var training : bool
Methods
def forward(self, input, hidden) ‑> Callable[..., Any]
-
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the :class:
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.Expand source code
def forward(self, input, hidden): embeds = self.embedding(input) lstm_out, hidden = self.lstm1(embeds, hidden) out = self.fc(lstm_out) # flatten the output out = out.reshape(-1, self.vocab_size) return out, hidden
-
Expand source code
def init_hidden(self, batch_size, device): hidden = (torch.zeros(self.num_lstm_layers, batch_size, self.hidden_dim).to(device = device), torch.zeros(self.num_lstm_layers, batch_size, self.hidden_dim).to(device = device)) return hidden