File size: 7,612 Bytes
0b2b0ab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5086590
0b2b0ab
 
5086590
 
 
 
0b2b0ab
 
 
 
 
 
 
 
 
 
 
 
 
5086590
0b2b0ab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5086590
0b2b0ab
5086590
 
 
 
0b2b0ab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
import math
from inspect import isfunction
from functools import partial
import matplotlib.pyplot as plt
from tqdm.auto import tqdm
from einops import rearrange
import torch
from torch import nn, einsum
import torch.nn.functional as F


def exists(x):
    return x is not None


def default(val, d):
    if exists(val):
        return val
    return d() if isfunction(d) else d


class Residual(nn.Module):
    def __init__(self, fn):
        super().__init__()
        self.fn = fn

    def forward(self, x, *args, **kwargs):
        return self.fn(x, *args, **kwargs) + x


def Upsample(dim):
    return nn.ConvTranspose2d(dim, dim, 4, 2, 1)


def Downsample(dim):
    return nn.Conv2d(dim, dim, 4, 2, 1)


class SinusoidalPositionEmbeddings(nn.Module):
    def __init__(self, dim):
        super().__init__()
        self.dim = dim

    def forward(self, time):
        device = time.device
        half_dim = self.dim // 2
        embeddings = math.log(10000) / (half_dim - 1)
        embeddings = torch.exp(torch.arange(half_dim, device=device) * -embeddings)
        embeddings = time[:, None] * embeddings[None, :]
        embeddings = torch.cat((embeddings.sin(), embeddings.cos()), dim=-1)
        return embeddings


class Block(nn.Module):
    def __init__(self, dim, dim_out, groups=8):
        super().__init__()
        self.proj = nn.Conv2d(dim, dim_out, 3, padding=1)
        self.norm = nn.GroupNorm(groups, dim_out)
        self.act = nn.SiLU()

    def forward(self, x, scale_shift=None):
        x = self.proj(x)
        x = self.norm(x)

        if exists(scale_shift):
            scale, shift = scale_shift
            x = x * (scale + 1) + shift

        x = self.act(x)
        return x


class ResnetBlock(nn.Module):
    """https://arxiv.org/abs/1512.03385"""

    def __init__(self, dim, dim_out, *, time_emb_dim=None, groups=8):
        super().__init__()
        self.mlp = (
            nn.Sequential(nn.SiLU(), nn.Linear(time_emb_dim, dim_out))
            if exists(time_emb_dim)
            else None
        )

        self.block1 = Block(dim, dim_out, groups=groups)
        self.block2 = Block(dim_out, dim_out, groups=groups)
        self.res_conv = nn.Conv2d(dim, dim_out, 1) if dim != dim_out else nn.Identity()

    def forward(self, x, time_emb=None):
        h = self.block1(x)

        if exists(self.mlp) and exists(time_emb):
            time_emb = self.mlp(time_emb)
            h = rearrange(time_emb, "b c -> b c 1 1") + h

        h = self.block2(h)
        return h + self.res_conv(x)


class ConvNextBlock(nn.Module):
    """https://arxiv.org/abs/2201.03545"""

    def __init__(self, dim, dim_out, *, time_emb_dim=None, mult=2, norm=True):
        super().__init__()
        self.mlp = (
            nn.Sequential(nn.GELU(), nn.Linear(time_emb_dim, dim))
            if exists(time_emb_dim)
            else None
        )

        self.ds_conv = nn.Conv2d(dim, dim, 7, padding=3, groups=dim)

        self.net = nn.Sequential(
            nn.GroupNorm(1, dim) if norm else nn.Identity(),
            nn.Conv2d(dim, dim_out * mult, 3, padding=1),
            nn.GELU(),
            nn.GroupNorm(1, dim_out * mult),
            nn.Conv2d(dim_out * mult, dim_out, 3, padding=1),
        )

        self.res_conv = nn.Conv2d(dim, dim_out, 1) if dim != dim_out else nn.Identity()

    def forward(self, x, time_emb=None):
        h = self.ds_conv(x)

        if exists(self.mlp) and exists(time_emb):
            assert exists(time_emb), "time embedding must be passed in"
            condition = self.mlp(time_emb)
            h = h + rearrange(condition, "b c -> b c 1 1")

        h = self.net(h)
        return h + self.res_conv(x)


class Attention(nn.Module):
    def __init__(self, dim, heads=4, dim_head=32):
        super().__init__()
        self.scale = dim_head**-0.5
        self.heads = heads
        hidden_dim = dim_head * heads
        self.to_qkv = nn.Conv2d(dim, hidden_dim * 3, 1, bias=False)
        self.to_q = nn.Conv2d(dim, hidden_dim, 1, bias=False)
        self.to_k = nn.Conv2d(dim, hidden_dim, 1, bias=False)
        self.to_v = nn.Conv2d(dim, hidden_dim, 1, bias=False)
        self.to_out = nn.Conv2d(hidden_dim, dim, 1)

    def forward(self, x):
        b, c, h, w = x.shape

        qkv = self.to_qkv(x).chunk(3, dim=1)
        q, k, v = map(
            lambda t: rearrange(t, "b (h c) x y -> b h c (x y)", h=self.heads), qkv
        )
        q = q * self.scale

        sim = einsum("b h d i, b h d j -> b h i j", q, k)
        sim = sim - sim.amax(dim=-1, keepdim=True).detach()
        attn = sim.softmax(dim=-1)

        out = einsum("b h i j, b h d j -> b h i d", attn, v)
        out = rearrange(out, "b h (x y) d -> b (h d) x y", x=h, y=w)

        return self.to_out(out)


class LinearCrossAttention(nn.Module):
    def __init__(self, dim, heads=4, dim_head=32) -> None:
        super().__init__()
        self.scale = dim_head**-0.5
        self.heads = heads
        hidden_dim = dim_head * heads
        self.to_kv = nn.Conv2d(dim, hidden_dim * 2, 1, bias=False)
        self.to_q = nn.Conv2d(dim, hidden_dim, 1, bias=False)
        self.out = nn.Conv2d(hidden_dim, dim, 1)

    def forward(self, x, cross_attend):
        b, c, h, w = x.shape
        q = self.to_q(x)
        k, v = self.to_kv(cross_attend).chunk(2, dim=1)
        q = rearrange(q, "b (h c) x y -> b h c (x y)", h=self.heads)
        k = rearrange(k, "b (h c) x y -> b h c (x y)", h=self.heads)
        v = rearrange(v, "b (h c) x y -> b h c (x y)", h=self.heads)
        q = q * self.scale
        sim = einsum("b h d i, b h d j -> b h i j", q, k)
        sim = sim - sim.amax(dim=-1, keepdim=True).detach()
        attn = sim.softmax(dim=-1)
        out = einsum("b h i j, b h d j -> b h i d", attn, v)
        out = rearrange(out, "b h (x y) d -> b (h d) x y", x=h, y=w)
        return self.out(out)


class LinearAttention(nn.Module):
    def __init__(self, dim, heads=4, dim_head=32):
        super().__init__()
        self.scale = dim_head**-0.5
        self.heads = heads
        hidden_dim = dim_head * heads
        self.to_qkv = nn.Conv2d(dim, hidden_dim * 3, 1, bias=False)
        self.to_q = nn.Conv2d(dim, hidden_dim, 1, bias=False)
        self.to_k = nn.Conv2d(dim, hidden_dim, 1, bias=False)
        self.to_v = nn.Conv2d(dim, hidden_dim, 1, bias=False)
        self.to_out = nn.Sequential(nn.Conv2d(hidden_dim, dim, 1), nn.GroupNorm(1, dim))

    def forward(self, x):
        b, c, h, w = x.shape
        qkv = self.to_qkv(x).chunk(3, dim=1)
        q, k, v = map(
            lambda t: rearrange(t, "b (h c) x y -> b h c (x y)", h=self.heads), qkv
        )
        # calculate the softmax with respect to columns softmax of equivalent to q^T with respect to last dim
        q = q.softmax(dim=-2)
        # calculate the softmax with respect to rows of k
        k = k.softmax(dim=-1)
        # normalize the values in the attention matrix
        q = q * self.scale
        # dot product of q and v matrices
        context = torch.einsum("b h d n, b h e n -> b h d e", k, v)
        # dot product of context and q
        out = torch.einsum("b h d e, b h d n -> b h e n", context, q)
        # rearrange the output to match the pytorch convention
        out = rearrange(out, "b h c (x y) -> b (h c) x y", h=self.heads, x=h, y=w)
        return self.to_out(out)


class PreNorm(nn.Module):
    def __init__(self, dim, fn):
        super().__init__()
        self.fn = fn
        self.norm = nn.GroupNorm(1, dim)

    def forward(self, x, *args, **kwargs):
        x = self.norm(x)
        return self.fn(x, *args, **kwargs)