File size: 6,763 Bytes
a256709
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
200
201
202
203
204
205
206
207
208
209
210
211
"""
Code modified from DETR tranformer:
https://github.com/facebookresearch/detr
Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
"""

import copy
from typing import Optional, List
import pickle as cp

import torch
import torch.nn.functional as F
from torch import nn, Tensor


class TransformerDecoder(nn.Module):
    def __init__(self, decoder_layer, num_layers, norm=None, return_intermediate=False):
        super().__init__()
        self.layers = _get_clones(decoder_layer, num_layers)
        self.num_layers = num_layers
        self.norm = norm
        self.return_intermediate = return_intermediate

    def forward(
        self,
        tgt,
        memory,
        tgt_mask: Optional[Tensor] = None,
        memory_mask: Optional[Tensor] = None,
        tgt_key_padding_mask: Optional[Tensor] = None,
        memory_key_padding_mask: Optional[Tensor] = None,
        pos: Optional[Tensor] = None,
        query_pos: Optional[Tensor] = None,
    ):
        output = tgt
        T, B, C = memory.shape
        intermediate = []
        atten_layers = []
        for n, layer in enumerate(self.layers):

            residual = True
            output, ws = layer(
                output,
                memory,
                tgt_mask=tgt_mask,
                memory_mask=memory_mask,
                tgt_key_padding_mask=tgt_key_padding_mask,
                memory_key_padding_mask=memory_key_padding_mask,
                pos=pos,
                query_pos=query_pos,
                residual=residual,
            )
            atten_layers.append(ws)
            if self.return_intermediate:
                intermediate.append(self.norm(output))
        if self.norm is not None:
            output = self.norm(output)
            if self.return_intermediate:
                intermediate.pop()
                intermediate.append(output)

        if self.return_intermediate:
            return torch.stack(intermediate)
        return output, atten_layers


class TransformerDecoderLayer(nn.Module):
    def __init__(
        self,
        d_model,
        nhead,
        dim_feedforward=2048,
        dropout=0.1,
        activation="relu",
        normalize_before=False,
    ):
        super().__init__()
        self.self_attn = nn.MultiheadAttention(d_model, nhead, 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.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.norm3 = nn.LayerNorm(d_model)
        self.dropout1 = nn.Dropout(dropout)
        self.dropout2 = nn.Dropout(dropout)
        self.dropout3 = nn.Dropout(dropout)

        self.activation = _get_activation_fn(activation)
        self.normalize_before = normalize_before

    def with_pos_embed(self, tensor, pos: Optional[Tensor]):
        return tensor if pos is None else tensor + pos

    def forward_post(
        self,
        tgt,
        memory,
        tgt_mask: Optional[Tensor] = None,
        memory_mask: Optional[Tensor] = None,
        tgt_key_padding_mask: Optional[Tensor] = None,
        memory_key_padding_mask: Optional[Tensor] = None,
        pos: Optional[Tensor] = None,
        query_pos: Optional[Tensor] = None,
        residual=True,
    ):
        q = k = self.with_pos_embed(tgt, query_pos)
        tgt2, ws = self.self_attn(
            q, k, value=tgt, attn_mask=tgt_mask, key_padding_mask=tgt_key_padding_mask
        )
        tgt = self.norm1(tgt)
        tgt2, ws = self.multihead_attn(
            query=self.with_pos_embed(tgt, query_pos),
            key=self.with_pos_embed(memory, pos),
            value=memory,
            attn_mask=memory_mask,
            key_padding_mask=memory_key_padding_mask,
        )

        # attn_weights [B,NUM_Q,T]
        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, ws

    def forward_pre(
        self,
        tgt,
        memory,
        tgt_mask: Optional[Tensor] = None,
        memory_mask: Optional[Tensor] = None,
        tgt_key_padding_mask: Optional[Tensor] = None,
        memory_key_padding_mask: Optional[Tensor] = None,
        pos: Optional[Tensor] = None,
        query_pos: Optional[Tensor] = None,
    ):
        tgt2 = self.norm1(tgt)
        q = k = self.with_pos_embed(tgt2, query_pos)
        tgt2, ws = self.self_attn(
            q, k, value=tgt2, attn_mask=tgt_mask, key_padding_mask=tgt_key_padding_mask
        )
        tgt = tgt + self.dropout1(tgt2)
        tgt2 = self.norm2(tgt)
        tgt2, attn_weights = self.multihead_attn(
            query=self.with_pos_embed(tgt2, query_pos),
            key=self.with_pos_embed(memory, pos),
            value=memory,
            attn_mask=memory_mask,
            key_padding_mask=memory_key_padding_mask,
        )
        tgt = tgt + self.dropout2(tgt2)
        tgt2 = self.norm3(tgt)
        tgt2 = self.linear2(self.dropout(self.activation(self.linear1(tgt2))))
        tgt = tgt + self.dropout3(tgt2)
        return tgt, attn_weights

    def forward(
        self,
        tgt,
        memory,
        tgt_mask: Optional[Tensor] = None,
        memory_mask: Optional[Tensor] = None,
        tgt_key_padding_mask: Optional[Tensor] = None,
        memory_key_padding_mask: Optional[Tensor] = None,
        pos: Optional[Tensor] = None,
        query_pos: Optional[Tensor] = None,
        residual=True,
    ):
        if self.normalize_before:
            return self.forward_pre(
                tgt,
                memory,
                tgt_mask,
                memory_mask,
                tgt_key_padding_mask,
                memory_key_padding_mask,
                pos,
                query_pos,
            )
        return self.forward_post(
            tgt,
            memory,
            tgt_mask,
            memory_mask,
            tgt_key_padding_mask,
            memory_key_padding_mask,
            pos,
            query_pos,
            residual,
        )


def _get_clones(module, N):
    return nn.ModuleList([copy.deepcopy(module) for i in range(N)])


def _get_activation_fn(activation):
    """Return an activation function given a string"""
    if activation == "relu":
        return F.relu
    if activation == "gelu":
        return F.gelu
    if activation == "glu":
        return F.glu
    raise RuntimeError(f"activation should be relu/gelu, not {activation}.")