1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
|
# The model is from here:
# https://github.com/pytorch/examples/blob/master/word_language_model/model.py
from typing import Optional, Tuple
import torch
import torch.nn as nn
from torch import Tensor
class RNNModel(nn.Module):
"""Container module with an encoder, a recurrent module, and a decoder."""
def __init__(
self,
rnn_type,
ntoken,
ninp,
nhid,
nlayers,
dropout=0.5,
tie_weights=False,
batchsize=2,
):
super().__init__()
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']"""
) from None
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
self.hidden = self.init_hidden(batchsize)
@staticmethod
def repackage_hidden(h):
"""Detach hidden states from their history."""
if isinstance(h, torch.Tensor):
return h.detach()
else:
return tuple([RNNModel.repackage_hidden(v) for v in h])
def init_weights(self):
initrange = 0.1
self.encoder.weight.data.uniform_(-initrange, initrange)
self.decoder.bias.data.fill_(0)
self.decoder.weight.data.uniform_(-initrange, initrange)
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.view(output.size(0) * output.size(1), output.size(2))
)
self.hidden = RNNModel.repackage_hidden(hidden)
return decoded.view(output.size(0), output.size(1), decoded.size(1))
def init_hidden(self, bsz):
weight = next(self.parameters()).data
if self.rnn_type == "LSTM":
return (
weight.new(self.nlayers, bsz, self.nhid).zero_(),
weight.new(self.nlayers, bsz, self.nhid).zero_(),
)
else:
return weight.new(self.nlayers, bsz, self.nhid).zero_()
class RNNModelWithTensorHidden(RNNModel):
"""Supports GRU scripting."""
@staticmethod
def repackage_hidden(h):
"""Detach hidden states from their history."""
return h.detach()
def forward(self, input: Tensor, hidden: Tensor):
emb = self.drop(self.encoder(input))
output, hidden = self.rnn(emb, hidden)
output = self.drop(output)
decoded = self.decoder(
output.view(output.size(0) * output.size(1), output.size(2))
)
self.hidden = RNNModelWithTensorHidden.repackage_hidden(hidden)
return decoded.view(output.size(0), output.size(1), decoded.size(1))
class RNNModelWithTupleHidden(RNNModel):
"""Supports LSTM scripting."""
@staticmethod
def repackage_hidden(h: Tuple[Tensor, Tensor]):
"""Detach hidden states from their history."""
return (h[0].detach(), h[1].detach())
def forward(self, input: Tensor, hidden: Optional[Tuple[Tensor, Tensor]] = None):
emb = self.drop(self.encoder(input))
output, hidden = self.rnn(emb, hidden)
output = self.drop(output)
decoded = self.decoder(
output.view(output.size(0) * output.size(1), output.size(2))
)
self.hidden = self.repackage_hidden(tuple(hidden))
return decoded.view(output.size(0), output.size(1), decoded.size(1))
|
