Spaces:
Running
on
Zero
Running
on
Zero
File size: 6,599 Bytes
1da48bb |
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 |
import logging
import math
from collections import OrderedDict
from functools import partial
from typing import Callable, List, Optional, Sequence, Tuple, Union
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint
from torch.jit import Final
from .config import use_fused_attn
from .helpers import to_2tuple
__all__ = ['VisionTransformer'] # model_registry will add each entrypoint fn to this
_logger = logging.getLogger(__name__)
def drop_path(x, drop_prob: float = 0., training: bool = False, scale_by_keep: bool = True):
"""Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
'survival rate' as the argument.
"""
if drop_prob == 0. or not training:
return x
keep_prob = 1 - drop_prob
shape = (x.shape[0],) + (1,) * (x.ndim - 1) # work with diff dim tensors, not just 2D ConvNets
random_tensor = x.new_empty(shape).bernoulli_(keep_prob)
if keep_prob > 0.0 and scale_by_keep:
random_tensor.div_(keep_prob)
return x * random_tensor
class DropPath(nn.Module):
"""Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
"""
def __init__(self, drop_prob: float = 0., scale_by_keep: bool = True):
super(DropPath, self).__init__()
self.drop_prob = drop_prob
self.scale_by_keep = scale_by_keep
def forward(self, x):
return drop_path(x, self.drop_prob, self.training, self.scale_by_keep)
def extra_repr(self):
return f'drop_prob={round(self.drop_prob,3):0.3f}'
class Attention(nn.Module):
fused_attn: Final[bool]
def __init__(
self,
dim,
num_heads=8,
qkv_bias=False,
qk_norm=False,
attn_drop=0.,
proj_drop=0.,
norm_layer=nn.LayerNorm,
):
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):
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,
)
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, init_values=1e-5, inplace=False):
super().__init__()
self.inplace = inplace
self.gamma = nn.Parameter(init_values * torch.ones(dim))
def forward(self, x):
return x.mul_(self.gamma) if self.inplace else x * self.gamma
class Mlp(nn.Module):
""" MLP as used in Vision Transformer, MLP-Mixer and related networks
"""
def __init__(
self,
in_features,
hidden_features=None,
out_features=None,
act_layer=nn.GELU,
norm_layer=None,
bias=True,
drop=0.,
use_conv=False,
):
super().__init__()
out_features = out_features or in_features
hidden_features = hidden_features or in_features
bias = to_2tuple(bias)
drop_probs = to_2tuple(drop)
linear_layer = partial(nn.Conv2d, kernel_size=1) if use_conv else nn.Linear
self.fc1 = linear_layer(in_features, hidden_features, bias=bias[0])
self.act = act_layer()
self.drop1 = nn.Dropout(drop_probs[0])
self.norm = norm_layer(hidden_features) if norm_layer is not None else nn.Identity()
self.fc2 = linear_layer(hidden_features, out_features, bias=bias[1])
self.drop2 = nn.Dropout(drop_probs[1])
def forward(self, x):
x = self.fc1(x)
x = self.act(x)
x = self.drop1(x)
x = self.fc2(x)
x = self.drop2(x)
return x
class Block(nn.Module):
def __init__(
self,
dim,
num_heads,
mlp_ratio=4.,
qkv_bias=False,
qk_norm=False,
proj_drop=0.,
attn_drop=0.,
init_values=None,
drop_path=0.,
act_layer=nn.GELU,
norm_layer=nn.LayerNorm,
mlp_layer=Mlp,
):
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. 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. else nn.Identity()
def forward(self, x):
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
|