File size: 8,754 Bytes
01bb3bb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
import math

import torch
import torch.nn.functional as F
from torch import nn
from torch.nn.modules.transformer import _get_activation_fn, _get_clones


class TransformerDecoder(nn.Module):
    r"""TransformerDecoder is a stack of N decoder layers

    Args:
        decoder_layer: an instance of the TransformerDecoderLayer() class (required).
        num_layers: the number of sub-decoder-layers in the decoder (required).
        norm: the layer normalization component (optional).

    Examples::
        >>> decoder_layer = nn.TransformerDecoderLayer(d_model=512, nhead=8)
        >>> transformer_decoder = nn.TransformerDecoder(decoder_layer, num_layers=6)
        >>> memory = torch.rand(10, 32, 512)
        >>> tgt = torch.rand(20, 32, 512)
        >>> out = transformer_decoder(tgt, memory)
    """
    __constants__ = ['norm']

    def __init__(self, decoder_layer, num_layers, norm=None):
        super(TransformerDecoder, self).__init__()
        self.layers = _get_clones(decoder_layer, num_layers)
        self.num_layers = num_layers
        self.norm = norm

    def forward(self, tgt, memory, memory2=None, tgt_mask=None,
                memory_mask=None, memory_mask2=None, tgt_key_padding_mask=None,
                memory_key_padding_mask=None, memory_key_padding_mask2=None):
        # type: (Tensor, Tensor, Optional[Tensor], Optional[Tensor], Optional[Tensor], Optional[Tensor]) -> Tensor
        r"""Pass the inputs (and mask) through the decoder layer in turn.

        Args:
            tgt: the sequence to the decoder (required).
            memory: the sequence from the last layer of the encoder (required).
            tgt_mask: the mask for the tgt sequence (optional).
            memory_mask: the mask for the memory sequence (optional).
            tgt_key_padding_mask: the mask for the tgt keys per batch (optional).
            memory_key_padding_mask: the mask for the memory keys per batch (optional).

        Shape:
            see the docs in Transformer class.
        """
        output = tgt

        for mod in self.layers:
            output = mod(output, memory, memory2=memory2, tgt_mask=tgt_mask,
                         memory_mask=memory_mask, memory_mask2=memory_mask2,
                         tgt_key_padding_mask=tgt_key_padding_mask,
                         memory_key_padding_mask=memory_key_padding_mask,
                         memory_key_padding_mask2=memory_key_padding_mask2)

        if self.norm is not None:
            output = self.norm(output)

        return output


class TransformerDecoderLayer(nn.Module):
    r"""TransformerDecoderLayer is made up of self-attn, multi-head-attn and feedforward network.
    This standard decoder layer is based on the paper "Attention Is All You Need".
    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez,
    Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in
    Neural Information Processing Systems, pages 6000-6010. Users may modify or implement
    in a different way during application.

    Args:
        d_model: the number of expected features in the input (required).
        nhead: the number of heads in the multiheadattention models (required).
        dim_feedforward: the dimension of the feedforward network model (default=2048).
        dropout: the dropout value (default=0.1).
        activation: the activation function of intermediate layer, relu or gelu (default=relu).

    Examples::
        >>> decoder_layer = nn.TransformerDecoderLayer(d_model=512, nhead=8)
        >>> memory = torch.rand(10, 32, 512)
        >>> tgt = torch.rand(20, 32, 512)
        >>> out = decoder_layer(tgt, memory)
    """

    def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1,
                 activation="relu", self_attn=True, siamese=False, debug=False):
        super().__init__()
        self.has_self_attn, self.siamese = self_attn, siamese
        self.debug = debug
        if self.has_self_attn:
            self.self_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
            self.norm1 = nn.LayerNorm(d_model)
            self.dropout1 = nn.Dropout(dropout)
        self.multihead_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
        # Implementation of Feedforward model
        self.linear1 = nn.Linear(d_model, dim_feedforward)
        self.dropout = nn.Dropout(dropout)
        self.linear2 = nn.Linear(dim_feedforward, d_model)

        self.norm2 = nn.LayerNorm(d_model)
        self.norm3 = nn.LayerNorm(d_model)
        self.dropout2 = nn.Dropout(dropout)
        self.dropout3 = nn.Dropout(dropout)
        if self.siamese:
            self.multihead_attn2 = nn.MultiheadAttention(d_model, nhead, dropout=dropout)

        self.activation = _get_activation_fn(activation)

    def __setstate__(self, state):
        if 'activation' not in state:
            state['activation'] = F.relu
        super().__setstate__(state)

    def forward(self, tgt, memory, tgt_mask=None, memory_mask=None,
                tgt_key_padding_mask=None, memory_key_padding_mask=None,
                memory2=None, memory_mask2=None, memory_key_padding_mask2=None):
        # type: (Tensor, Tensor, Optional[Tensor], Optional[Tensor], Optional[Tensor], Optional[Tensor]) -> Tensor
        r"""Pass the inputs (and mask) through the decoder layer.

        Args:
            tgt: the sequence to the decoder layer (required).
            memory: the sequence from the last layer of the encoder (required).
            tgt_mask: the mask for the tgt sequence (optional).
            memory_mask: the mask for the memory sequence (optional).
            tgt_key_padding_mask: the mask for the tgt keys per batch (optional).
            memory_key_padding_mask: the mask for the memory keys per batch (optional).

        Shape:
            see the docs in Transformer class.
        """
        if self.has_self_attn:
            tgt2, attn = self.self_attn(tgt, tgt, tgt, attn_mask=tgt_mask,
                                        key_padding_mask=tgt_key_padding_mask)
            tgt = tgt + self.dropout1(tgt2)
            tgt = self.norm1(tgt)
            if self.debug: self.attn = attn
        tgt2, attn2 = self.multihead_attn(tgt, memory, memory, attn_mask=memory_mask,
                                          key_padding_mask=memory_key_padding_mask)
        if self.debug: self.attn2 = attn2

        if self.siamese:
            tgt3, attn3 = self.multihead_attn2(tgt, memory2, memory2, attn_mask=memory_mask2,
                                               key_padding_mask=memory_key_padding_mask2)
            tgt = tgt + self.dropout2(tgt3)
            if self.debug: self.attn3 = attn3

        tgt = tgt + self.dropout2(tgt2)
        tgt = self.norm2(tgt)
        tgt2 = self.linear2(self.dropout(self.activation(self.linear1(tgt))))
        tgt = tgt + self.dropout3(tgt2)
        tgt = self.norm3(tgt)

        return tgt


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)
    """

    def __init__(self, d_model, dropout=0.1, max_len=5000):
        super().__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)

    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)