pytorch代码实现注意力机制之MHSA

MHSA注意力机制

MHSA是多头自注意力机制(Multi-Head Self-Altention)，是自然语言处理领域中用于语言模型中的一种特殊机制。它能够让模型在预测下一个词的时候，更好地关注句子中不同位置的词，以适应不同的语言场景。MHSA的核心思想是将一个线性变换分成多个头，每个头执行自注意力操作，并将所有头的输出拼接在一起作为最终的表示。在自注意力操作中，每个头都计算出一个注意力矩阵，该矩阵在整个序列中对不同位置的词进行加权求和，以得到每个位置的表示。MHSA的应用已被证明在许多自然语言处理任务中具有很好的效果。

论文地址：MHSA注意力机制原论文

代码实现：

import torch
import torch.nn as nn

class MHSA(nn.Module):
    def __init__(self, n_dims, width=14, height=14, heads=4, pos_emb=False):
        super(MHSA, self).__init__()

        self.heads = heads
        self.query = nn.Conv2d(n_dims, n_dims, kernel_size=1)
        self.key = nn.Conv2d(n_dims, n_dims, kernel_size=1)
        self.value = nn.Conv2d(n_dims, n_dims, kernel_size=1)
        self.pos = pos_emb
        if self.pos:
            self.rel_h_weight = nn.Parameter(torch.randn([1, heads, (n_dims) // heads, 1, int(height)]),
                                             requires_grad=True)
            self.rel_w_weight = nn.Parameter(torch.randn([1, heads, (n_dims) // heads, int(width), 1]),
                                             requires_grad=True)
        self.softmax = nn.Softmax(dim=-1)

    def forward(self, x):
        n_batch, C, width, height = x.size()
        q = self.query(x).view(n_batch, self.heads, C // self.heads, -1)
        k = self.key(x).view(n_batch, self.heads, C // self.heads, -1)
        v = self.value(x).view(n_batch, self.heads, C // self.heads, -1)
        content_content = torch.matmul(q.permute(0, 1, 3, 2), k)  # 1,C,h*w,h*w
        c1, c2, c3, c4 = content_content.size()
        if self.pos:
            content_position = (self.rel_h_weight + self.rel_w_weight).view(1, self.heads, C // self.heads, -1).permute(
                0, 1, 3, 2)  # 1,4,1024,64

            content_position = torch.matmul(content_position, q)  # ([1, 4, 1024, 256])
            content_position = content_position if (
                    content_content.shape == content_position.shape) else content_position[:, :, :c3, ]
            assert (content_content.shape == content_position.shape)
            energy = content_content + content_position
        else:
            energy = content_content
        attention = self.softmax(energy)
        out = torch.matmul(v, attention.permute(0, 1, 3, 2))  # 1,4,256,64
        out = out.view(n_batch, C, width, height)
        return out

if __name__ == '__main__':
    input = torch.randn(50, 512, 7, 7)
    mhsa = MHSA(n_dims=512)
    output = mhsa(input)
    print(output.shape)