Transformer and Self-Attention Pytorch代码

下面是一个使用 PyTorch 实现 Transformer 和 Self-Attention 的示例代码：

首先，我们需要导入所需的库：

import torch
import torch.nn as nn
import torch.nn.functional as F

然后，我们定义一个 Self-Attention 类：

class SelfAttention(nn.Module):
    def __init__(self, embed_size, heads):
        super(SelfAttention, self).__init__()
        self.embed_size = embed_size
        self.heads = heads
        self.head_dim = embed_size // heads
        
        assert (self.head_dim * heads == embed_size), "Embed size needs to be divisible by heads"
        
        self.values = nn.Linear(self.head_dim, self.head_dim, bias=False)
        self.keys = nn.Linear(self.head_dim, self.head_dim, bias=False)
        self.queries = nn.Linear(self.head_dim, self.head_dim, bias=False)
        self.fc_out = nn.Linear(heads*self.head_dim, embed_size)
        
    def forward(self, values, keys, query, mask):
        N = query.shape[0]
        value_len, key_len, query_len = values.shape[1], keys.shape[1], query.shape[1]
        
        # Split embedding into self.heads pieces
        values = values.reshape(N, value_len, self.heads, self.head_dim)
        keys = keys.reshape(N, key_len, self.heads, self.head_dim)
        query = query.reshape(N, query_len, self.heads, self.head_dim)
        
        values = self.values(values)  # (N, value_len, heads, head_dim)
        keys = self.keys(keys)  # (N, key_len, heads, head_dim)
        query = self.queries(query)  # (N, query_len, heads, heads_dim)
        
        # Compute dot product attention
        energy = torch.einsum("nqhd,nkhd->nhqk", [query, keys])
        # energy shape: (N, heads, query_len, key_len)
        
        if mask is not None:
            energy = energy.masked_fill(mask == 0, float("-1e20"))
        
        attention = torch.softmax(energy / (self.embed_size ** (1/2)), dim=3)
        
        # Compute attention output
        out = torch.einsum("nhql,nlhd->nqhd", [attention, values]).reshape(
            N, query_len, self.heads*self.head_dim
        )
        
        out = self.fc_out(out)
        
        return out

接下来，我们定义一个 TransformerBlock 类：

class TransformerBlock(nn.Module):
    def __init__(self, embed_size, heads, dropout, forward_expansion):
        super(TransformerBlock, self).__init__()
        self.attention = SelfAttention(embed_size, heads)
        self.norm1 = nn.LayerNorm(embed_size)
        self.norm2 = nn.LayerNorm(embed_size)
        
        self.feed_forward = nn.Sequential(
            nn.Linear(embed_size, forward_expansion*embed_size),
            nn.ReLU(),
            nn.Linear(forward_expansion*embed_size, embed_size),
        )
        
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, value, key, query, mask):
        attention = self.attention(value, key, query, mask)
        
        x = self.dropout(self.norm1(attention + query))
        forward = self.feed_forward(x)
        
        out = self.dropout(self.norm2(forward + x))
        
        return out

最后，我们定义一个 TransformerEncoder 类：

class TransformerEncoder(nn.Module):
    def __init__(self, embed_size, heads, dropout, forward_expansion, num_layers):
        super(TransformerEncoder, self).__init__()
        self.layers = nn.ModuleList(
            [
                TransformerBlock(embed_size, heads, dropout, forward_expansion)
                for _ in range(num_layers)
            ]
        )
        
    def forward(self, x, mask):
        for layer in self.layers:
            x = layer(x, x, x, mask)
            
        return x

现在，我们已经定义了一个完整的 Transformer 模型，可以在实际应用中使用。