1:在attention is all you need 文章中,作者提出了多头注意力。
注意力公式:dk是K的维度。
多头公式:
VIT将多头注意力应用到了图像领域,所以具体看一下VIT关于多头注意力的代码实现。
class PatchEmbed(nn.Module):
def __init__(self, img_size=224, patch_size=16, in_c=3, embed_dim=768, norm_layer=None):
super().__init__()
img_size = (img_size, img_size)
patch_size = (patch_size, patch_size)
self.img_size = img_size
self.patch_size = patch_size
self.grid_size = (img_size[0] // patch_size[0], img_size[1] // patch_size[1])
self.num_patches = self.grid_size[0] * self.grid_size[1]
self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=patch_size, stride=patch_size)
self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()
def forward(self, x):
B, C, H, W = x.shape
assert H == self.img_size[0] and W == self.img_size[1], \
f"Input image size ({H}*{W}) doesn't match model ({self.img_size[0]}*{self.img_size[1]})."
# flatten: [B, C, H, W] -> [B, C, HW]
# transpose: [B, C, HW] -> [B, HW, C]
x = self.proj(x).flatten(2).transpose(1, 2)
x = self.norm(x)
return x
class Attention(nn.Module):
def __init__(self,
dim, # 输入token的dim
num_heads=8,
qkv_bias=False,
qk_scale=None,
attn_drop_ratio=0.,
proj_drop_ratio=0.):
super(Attention, self).__init__()
self.num_heads = num_heads
head_dim = dim // num_heads
self.scale = qk_scale or head_dim ** -0.5
self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
self.attn_drop = nn.Dropout(attn_drop_ratio)
self.proj = nn.Linear(dim, dim)
self.proj_drop = nn.Dropout(proj_drop_ratio)
def forward(self, x):
# [batch_size, num_patches + 1, total_embed_dim]
B, N, C = x.shape #(1,197,768)
# qkv(): -> [batch_size, num_patches + 1, 3 * total_embed_dim]
# reshape: -> [batch_size, num_patches + 1, 3, num_heads, embed_dim_per_head]
# permute: -> [3, batch_size, num_heads, num_patches + 1, embed_dim_per_head]
qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
# [batch_size, num_heads, num_patches + 1, embed_dim_per_head]
q, k, v = qkv[0], qkv[1], qkv[2] # make torchscript happy (cannot use tensor as tuple)
# transpose: -> [batch_size, num_heads, embed_dim_per_head, num_patches + 1]
# @: multiply -> [batch_size, num_heads, num_patches + 1, num_patches + 1]
attn = (q @ k.transpose(-2, -1)) * self.scale
attn = attn.softmax(dim=-1)
attn = self.attn_drop(attn)
# @: multiply -> [batch_size, num_heads, num_patches + 1, embed_dim_per_head]
# transpose: -> [batch_size, num_patches + 1, num_heads, embed_dim_per_head]
# reshape: -> [batch_size, num_patches + 1, total_embed_dim]
x = (attn @ v).transpose(1, 2).reshape(B, N, C)
x = self.proj(x)
x = self.proj_drop(x)
return x
class Block(nn.Module):
def __init__(self,
dim,
num_heads,
mlp_ratio=4.,
qkv_bias=False,
qk_scale=None,
drop_ratio=0.,
attn_drop_ratio=0.,
drop_path_ratio=0.,
act_layer=nn.GELU,
norm_layer=nn.LayerNorm):
super(Block, self).__init__()
self.norm1 = norm_layer(dim)
self.attn = Attention(dim, num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale,
attn_drop_ratio=attn_drop_ratio, proj_drop_ratio=drop_ratio)
# NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
self.drop_path = DropPath(drop_path_ratio) if drop_path_ratio > 0. else nn.Identity()
self.norm2 = norm_layer(dim)
mlp_hidden_dim = int(dim * mlp_ratio)
self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop_ratio)
def forward(self, x):
x = x + self.drop_path(self.attn(self.norm1(x)))
x = x + self.drop_path(self.mlp(self.norm2(x)))
return x
1:首先将图像进行分块。
2:然后进行注意力计算,首先获得q,k,v。
3:接着进行注意力计算
4:然后进行下一步处理:
5:这样整个Transformer encoder就结束了。