File size: 4,561 Bytes
9867d34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import math
import torch
import torch.nn as nn

from ...utils.helper import to_2tuple, to_1tuple

class PatchEmbed1D(nn.Module):
    """1D Audio to Patch Embedding

    A convolution based approach to patchifying a 1D audio w/ embedding projection.

    Based on the impl in https://github.com/google-research/vision_transformer

    Hacked together by / Copyright 2020 Ross Wightman
    """

    def __init__(
        self,
        patch_size=1,
        in_chans=768,
        embed_dim=768,
        norm_layer=None,
        flatten=True,
        bias=True,
        dtype=None,
        device=None,
    ):
        factory_kwargs = {"dtype": dtype, "device": device}
        super().__init__()
        patch_size = to_1tuple(patch_size)
        self.patch_size = patch_size
        self.flatten = flatten

        self.proj = nn.Conv1d(
            in_chans, embed_dim, kernel_size=patch_size, stride=patch_size, bias=bias, **factory_kwargs
        )
        nn.init.xavier_uniform_(self.proj.weight.view(self.proj.weight.size(0), -1))
        if bias:
            nn.init.zeros_(self.proj.bias)

        self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()

    def forward(self, x):
        assert (
            x.shape[2] % self.patch_size[0] == 0
        ), f"The patch_size of {self.patch_size[0]} must be divisible by the token number ({x.shape[2]}) of x."

        x = self.proj(x)
        if self.flatten:
            x = x.transpose(1, 2)  # BCN -> BNC
        x = self.norm(x)
        return x


class ConditionProjection(nn.Module):
    """
    Projects condition embeddings. Also handles dropout for classifier-free guidance.

    Adapted from https://github.com/PixArt-alpha/PixArt-alpha/blob/master/diffusion/model/nets/PixArt_blocks.py
    """

    def __init__(self, in_channels, hidden_size, act_layer, dtype=None, device=None):
        factory_kwargs = {'dtype': dtype, 'device': device}
        super().__init__()
        self.linear_1 = nn.Linear(in_features=in_channels, out_features=hidden_size, bias=True, **factory_kwargs)
        self.act_1 = act_layer()
        self.linear_2 = nn.Linear(in_features=hidden_size, out_features=hidden_size, bias=True, **factory_kwargs)

    def forward(self, caption):
        hidden_states = self.linear_1(caption)
        hidden_states = self.act_1(hidden_states)
        hidden_states = self.linear_2(hidden_states)
        return hidden_states


def timestep_embedding(t, dim, max_period=10000):
    """
    Create sinusoidal timestep embeddings.

    Args:
        t (torch.Tensor): a 1-D Tensor of N indices, one per batch element. These may be fractional.
        dim (int): the dimension of the output.
        max_period (int): controls the minimum frequency of the embeddings.

    Returns:
        embedding (torch.Tensor): An (N, D) Tensor of positional embeddings.

    .. ref_link: https://github.com/openai/glide-text2im/blob/main/glide_text2im/nn.py
    """
    half = dim // 2
    freqs = torch.exp(
        -math.log(max_period)
        * torch.arange(start=0, end=half, dtype=torch.float32)
        / half
    ).to(device=t.device)
    args = t[:, None].float() * freqs[None]
    embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
    if dim % 2:
        embedding = torch.cat(
            [embedding, torch.zeros_like(embedding[:, :1])], dim=-1
        )
    return embedding


class TimestepEmbedder(nn.Module):
    """
    Embeds scalar timesteps into vector representations.
    """
    def __init__(self,
                 hidden_size,
                 act_layer,
                 frequency_embedding_size=256,
                 max_period=10000,
                 out_size=None,
                 dtype=None,
                 device=None
                 ):
        factory_kwargs = {'dtype': dtype, 'device': device}
        super().__init__()
        self.frequency_embedding_size = frequency_embedding_size
        self.max_period = max_period
        if out_size is None:
            out_size = hidden_size

        self.mlp = nn.Sequential(
            nn.Linear(frequency_embedding_size, hidden_size, bias=True, **factory_kwargs),
            act_layer(),
            nn.Linear(hidden_size, out_size, bias=True, **factory_kwargs),
        )
        nn.init.normal_(self.mlp[0].weight, std=0.02)
        nn.init.normal_(self.mlp[2].weight, std=0.02)

    def forward(self, t):
        t_freq = timestep_embedding(t, self.frequency_embedding_size, self.max_period).type(self.mlp[0].weight.dtype)
        t_emb = self.mlp(t_freq)
        return t_emb