File size: 6,335 Bytes
093b0a5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import torch
import torch.nn as nn
import torch.nn.functional as F

import numpy as np

from math import sqrt
from utils.masking import TriangularCausalMask, ProbMask


class FullAttention(nn.Module):
    def __init__(
        self,
        mask_flag=True,
        factor=5,
        scale=None,
        attention_dropout=0.1,
        output_attention=False,
    ):
        super(FullAttention, self).__init__()
        self.scale = scale
        self.mask_flag = mask_flag
        self.output_attention = output_attention
        self.dropout = nn.Dropout(attention_dropout)

    def forward(self, queries, keys, values, attn_mask):
        B, L, H, E = queries.shape
        _, S, _, D = values.shape
        scale = self.scale or 1.0 / sqrt(E)

        scores = torch.einsum("blhe,bshe->bhls", queries, keys)
        if self.mask_flag:
            if attn_mask is None:
                attn_mask = TriangularCausalMask(B, L, device=queries.device)

            scores.masked_fill_(attn_mask.mask, -np.inf)

        A = self.dropout(torch.softmax(scale * scores, dim=-1))
        V = torch.einsum("bhls,bshd->blhd", A, values)

        if self.output_attention:
            return (V.contiguous(), A)
        else:
            return (V.contiguous(), None)


class ProbAttention(nn.Module):
    def __init__(
        self,
        mask_flag=True,
        factor=5,
        scale=None,
        attention_dropout=0.1,
        output_attention=False,
    ):
        super(ProbAttention, self).__init__()
        self.factor = factor
        self.scale = scale
        self.mask_flag = mask_flag
        self.output_attention = output_attention
        self.dropout = nn.Dropout(attention_dropout)

    def _prob_QK(self, Q, K, sample_k, n_top):  # n_top: c*ln(L_q)
        # Q [B, H, L, D]
        B, H, L_K, E = K.shape
        _, _, L_Q, _ = Q.shape

        # calculate the sampled Q_K
        K_expand = K.unsqueeze(-3).expand(B, H, L_Q, L_K, E)
        index_sample = torch.randint(
            L_K, (L_Q, sample_k)
        )  # real U = U_part(factor*ln(L_k))*L_q
        K_sample = K_expand[:, :, torch.arange(L_Q).unsqueeze(1), index_sample, :]
        Q_K_sample = torch.matmul(Q.unsqueeze(-2), K_sample.transpose(-2, -1)).squeeze(
            -2
        )

        # find the Top_k query with sparisty measurement
        M = Q_K_sample.max(-1)[0] - torch.div(Q_K_sample.sum(-1), L_K)
        M_top = M.topk(n_top, sorted=False)[1]

        # use the reduced Q to calculate Q_K
        Q_reduce = Q[
            torch.arange(B)[:, None, None], torch.arange(H)[None, :, None], M_top, :
        ]  # factor*ln(L_q)
        Q_K = torch.matmul(Q_reduce, K.transpose(-2, -1))  # factor*ln(L_q)*L_k

        return Q_K, M_top

    def _get_initial_context(self, V, L_Q):
        B, H, L_V, D = V.shape
        if not self.mask_flag:
            # V_sum = V.sum(dim=-2)
            V_sum = V.mean(dim=-2)
            contex = V_sum.unsqueeze(-2).expand(B, H, L_Q, V_sum.shape[-1]).clone()
        else:  # use mask
            assert L_Q == L_V  # requires that L_Q == L_V, i.e. for self-attention only
            contex = V.cumsum(dim=-2)
        return contex

    def _update_context(self, context_in, V, scores, index, L_Q, attn_mask):
        B, H, L_V, D = V.shape

        if self.mask_flag:
            attn_mask = ProbMask(B, H, L_Q, index, scores, device=V.device)
            scores.masked_fill_(attn_mask.mask, -np.inf)

        attn = torch.softmax(scores, dim=-1)  # nn.Softmax(dim=-1)(scores)

        context_in[
            torch.arange(B)[:, None, None], torch.arange(H)[None, :, None], index, :
        ] = torch.matmul(attn, V).type_as(context_in)
        if self.output_attention:
            attns = (torch.ones([B, H, L_V, L_V]) / L_V).type_as(attn).to(attn.device)
            attns[
                torch.arange(B)[:, None, None], torch.arange(H)[None, :, None], index, :
            ] = attn
            return (context_in, attns)
        else:
            return (context_in, None)

    def forward(self, queries, keys, values, attn_mask):
        B, L_Q, H, D = queries.shape
        _, L_K, _, _ = keys.shape

        queries = queries.transpose(2, 1)
        keys = keys.transpose(2, 1)
        values = values.transpose(2, 1)

        U_part = self.factor * np.ceil(np.log(L_K)).astype("int").item()  # c*ln(L_k)
        u = self.factor * np.ceil(np.log(L_Q)).astype("int").item()  # c*ln(L_q)

        U_part = U_part if U_part < L_K else L_K
        u = u if u < L_Q else L_Q

        scores_top, index = self._prob_QK(queries, keys, sample_k=U_part, n_top=u)

        # add scale factor
        scale = self.scale or 1.0 / sqrt(D)
        if scale is not None:
            scores_top = scores_top * scale
        # get the context
        context = self._get_initial_context(values, L_Q)
        # update the context with selected top_k queries
        context, attn = self._update_context(
            context, values, scores_top, index, L_Q, attn_mask
        )

        return context.transpose(2, 1).contiguous(), attn


class AttentionLayer(nn.Module):
    def __init__(
        self, attention, d_model, n_heads, d_keys=None, d_values=None, mix=False
    ):
        super(AttentionLayer, self).__init__()

        d_keys = d_keys or (d_model // n_heads)
        d_values = d_values or (d_model // n_heads)

        self.inner_attention = attention
        self.query_projection = nn.Linear(d_model, d_keys * n_heads)
        self.key_projection = nn.Linear(d_model, d_keys * n_heads)
        self.value_projection = nn.Linear(d_model, d_values * n_heads)
        self.out_projection = nn.Linear(d_values * n_heads, d_model)
        self.n_heads = n_heads
        self.mix = mix

    def forward(self, queries, keys, values, attn_mask):
        B, L, _ = queries.shape
        _, S, _ = keys.shape
        H = self.n_heads

        queries = self.query_projection(queries).view(B, L, H, -1)
        keys = self.key_projection(keys).view(B, S, H, -1)
        values = self.value_projection(values).view(B, S, H, -1)

        out, attn = self.inner_attention(queries, keys, values, attn_mask)
        if self.mix:
            # https://arxiv.org/pdf/2109.02789.pdf
            out = out.transpose(2, 1).contiguous()
        out = out.view(B, L, -1)

        return self.out_projection(out), attn