Attention Layer whether to play a role in the network feedforward?
I know, Attention plays a role in training， but it’s needed for testing?
I find the torch.nn.Dropout in the attention.
I think the Dropout layer may will not be used in testing.
class Attention(nn.Module):
def __init__(self, dim, heads=8, dim_head=64, dropout=0.):
super().__init__()
inner_dim = dim_head * heads
project_out = not (heads == 1 and dim_head == dim)
self.heads = heads
self.scale = dim_head ** -0.5
self.attend = nn.Softmax(dim=-1)
self.to_qkv = nn.Linear(dim, inner_dim * 3, bias=False)
self.to_out = nn.Sequential(
nn.Linear(inner_dim, dim),
nn.Dropout(dropout)
) if project_out else nn.Identity()
def forward(self, x):
qkv = self.to_qkv(x).chunk(3, dim=-1)
q, k, v = map(lambda t: rearrange(t, 'b p n (h d) -> b p h n d', h=self.heads), qkv)
dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
attn = self.attend(dots)
out = torch.matmul(attn, v)
out = rearrange(out, 'b p h n d -> b p n (h d)')
return self.to_out(out)