File size: 5,098 Bytes
3f50570 |
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 |
import torch.nn as nn
from typing import Optional
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint
from torch.jit import Final
from timm.layers import (
Mlp,
DropPath,
use_fused_attn,
)
class Attention(nn.Module):
fused_attn: Final[bool]
def __init__(
self,
dim: int,
num_heads: int = 8,
qkv_bias: bool = False,
qk_norm: bool = False,
attn_drop: float = 0.0,
proj_drop: float = 0.0,
norm_layer: nn.Module = nn.LayerNorm,
) -> None:
super().__init__()
assert dim % num_heads == 0, "dim should be divisible by num_heads"
self.num_heads = num_heads
self.head_dim = dim // num_heads
self.scale = self.head_dim**-0.5
self.fused_attn = use_fused_attn()
self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
self.q_norm = norm_layer(self.head_dim) if qk_norm else nn.Identity()
self.k_norm = norm_layer(self.head_dim) if qk_norm else nn.Identity()
self.attn_drop = nn.Dropout(attn_drop)
self.proj = nn.Linear(dim, dim)
self.proj_drop = nn.Dropout(proj_drop)
def forward(self, x: torch.Tensor) -> torch.Tensor:
B, N, C = x.shape
qkv = (
self.qkv(x)
.reshape(B, N, 3, self.num_heads, self.head_dim)
.permute(2, 0, 3, 1, 4)
)
q, k, v = qkv.unbind(0)
q, k = self.q_norm(q), self.k_norm(k)
if self.fused_attn:
x = F.scaled_dot_product_attention(
q,
k,
v,
dropout_p=self.attn_drop.p if self.training else 0.0,
)
else:
q = q * self.scale
attn = q @ k.transpose(-2, -1)
attn = attn.softmax(dim=-1)
attn = self.attn_drop(attn)
x = attn @ v
x = x.transpose(1, 2).reshape(B, N, C)
x = self.proj(x)
x = self.proj_drop(x)
return x
class LayerScale(nn.Module):
def __init__(
self,
dim: int,
init_values: float = 1e-5,
inplace: bool = False,
) -> None:
super().__init__()
self.inplace = inplace
self.gamma = nn.Parameter(init_values * torch.ones(dim))
def forward(self, x: torch.Tensor) -> torch.Tensor:
return x.mul_(self.gamma) if self.inplace else x * self.gamma
class TransformerBlock(nn.Module):
def __init__(
self,
dim: int,
num_heads: int,
mlp_ratio: float = 4.0,
qkv_bias: bool = False,
qk_norm: bool = False,
proj_drop: float = 0.0,
attn_drop: float = 0.0,
init_values: Optional[float] = None,
drop_path: float = 0.0,
act_layer: nn.Module = nn.GELU,
norm_layer: nn.Module = nn.LayerNorm,
mlp_layer: nn.Module = Mlp,
) -> None:
super().__init__()
self.norm1 = norm_layer(dim)
self.attn = Attention(
dim,
num_heads=num_heads,
qkv_bias=qkv_bias,
qk_norm=qk_norm,
attn_drop=attn_drop,
proj_drop=proj_drop,
norm_layer=norm_layer,
)
self.ls1 = (
LayerScale(dim, init_values=init_values) if init_values else nn.Identity()
)
self.drop_path1 = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()
self.norm2 = norm_layer(dim)
self.mlp = mlp_layer(
in_features=dim,
hidden_features=int(dim * mlp_ratio),
act_layer=act_layer,
drop=proj_drop,
)
self.ls2 = (
LayerScale(dim, init_values=init_values) if init_values else nn.Identity()
)
self.drop_path2 = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()
def forward(self, x: torch.Tensor) -> torch.Tensor:
x = x + self.drop_path1(self.ls1(self.attn(self.norm1(x))))
x = x + self.drop_path2(self.ls2(self.mlp(self.norm2(x))))
return x
class Transformer(nn.Module):
"""
Transformer layer, taken from timm library
"""
def __init__(
self,
embed_dim: int,
num_heads: int,
num_layers: int,
mlp_ratio: float = 4.0,
qkv_bias: bool = False,
qk_norm: bool = False,
proj_drop: float = 0.0,
attn_drop: float = 0.0,
drop_path: float = 0.0,
):
super(Transformer, self).__init__()
self.blocks = nn.ModuleList(
[
TransformerBlock(
dim=embed_dim,
num_heads=num_heads,
mlp_ratio=mlp_ratio,
qkv_bias=qkv_bias,
qk_norm=qk_norm,
proj_drop=proj_drop,
attn_drop=attn_drop,
drop_path=drop_path,
)
for _ in range(num_layers)
]
)
def forward(self, x):
for block in self.blocks:
x = block(x)
return x |