# Copy from https://github.com/pytorch/examples/tree/master/word_language_model
# BSD 3-Clause License (see THIRD-PARTY)
# flake8: noqa
import math
import torch
import torch.nn as nn
import torch.nn.functional as F
[docs]class RNNModel(nn.Module):
"""Container module with an encoder, a recurrent module, and a decoder."""
[docs] def __init__(self, rnn_type, ntoken, ninp, nhid, nlayers, dropout=0.5, tie_weights=False):
super(RNNModel, self).__init__()
self.ntoken = ntoken
self.drop = nn.Dropout(dropout)
self.encoder = nn.Embedding(ntoken, ninp)
if rnn_type in ['LSTM', 'GRU']:
self.rnn = getattr(nn, rnn_type)(ninp, nhid, nlayers, dropout=dropout)
else:
try:
nonlinearity = {'RNN_TANH': 'tanh', 'RNN_RELU': 'relu'}[rnn_type]
except KeyError:
raise ValueError( """An invalid option for `--model` was supplied,
options are ['LSTM', 'GRU', 'RNN_TANH' or 'RNN_RELU']""")
self.rnn = nn.RNN(ninp, nhid, nlayers, nonlinearity=nonlinearity, dropout=dropout)
self.decoder = nn.Linear(nhid, ntoken)
# Optionally tie weights as in:
# "Using the Output Embedding to Improve Language Models" (Press & Wolf 2016)
# https://arxiv.org/abs/1608.05859
# and
# "Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling" (Inan et al. 2016)
# https://arxiv.org/abs/1611.01462
if tie_weights:
if nhid != ninp:
raise ValueError('When using the tied flag, nhid must be equal to emsize')
self.decoder.weight = self.encoder.weight
self.init_weights()
self.rnn_type = rnn_type
self.nhid = nhid
self.nlayers = nlayers
def init_weights(self):
initrange = 0.1
nn.init.uniform_(self.encoder.weight, -initrange, initrange)
nn.init.zeros_(self.decoder.weight)
nn.init.uniform_(self.decoder.weight, -initrange, initrange)
[docs] def forward(self, input, hidden):
emb = self.drop(self.encoder(input))
output, hidden = self.rnn(emb, hidden)
output = self.drop(output)
decoded = self.decoder(output)
decoded = decoded.view(-1, self.ntoken)
return F.log_softmax(decoded, dim=1), hidden
def init_hidden(self, bsz):
weight = next(self.parameters())
if self.rnn_type == 'LSTM':
return (weight.new_zeros(self.nlayers, bsz, self.nhid),
weight.new_zeros(self.nlayers, bsz, self.nhid))
else:
return weight.new_zeros(self.nlayers, bsz, self.nhid)
# Temporarily leave PositionalEncoding module here. Will be moved somewhere else.
[docs]class PositionalEncoding(nn.Module):
r"""Inject some information about the relative or absolute position of the tokens
in the sequence. The positional encodings have the same dimension as
the embeddings, so that the two can be summed. Here, we use sine and cosine
functions of different frequencies.
.. math::
\text{PosEncoder}(pos, 2i) = sin(pos/10000^(2i/d_model))
\text{PosEncoder}(pos, 2i+1) = cos(pos/10000^(2i/d_model))
\text{where pos is the word position and i is the embed idx)
Args:
d_model: the embed dim (required).
dropout: the dropout value (default=0.1).
max_len: the max. length of the incoming sequence (default=5000).
Examples:
>>> pos_encoder = PositionalEncoding(d_model)
"""
[docs] def __init__(self, d_model, dropout=0.1, max_len=5000):
super(PositionalEncoding, self).__init__()
self.dropout = nn.Dropout(p=dropout)
pe = torch.zeros(max_len, d_model)
position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
div_term = torch.exp(torch.arange(0, d_model, 2).float() * (-math.log(10000.0) / d_model))
pe[:, 0::2] = torch.sin(position * div_term)
pe[:, 1::2] = torch.cos(position * div_term)
pe = pe.unsqueeze(0).transpose(0, 1)
self.register_buffer('pe', pe)
[docs] def forward(self, x):
r"""Inputs of forward function
Args:
x: the sequence fed to the positional encoder model (required).
Shape:
x: [sequence length, batch size, embed dim]
output: [sequence length, batch size, embed dim]
Examples:
>>> output = pos_encoder(x)
"""
x = x + self.pe[:x.size(0), :]
return self.dropout(x)