Transformer 参数量计算

参考

https://blog.youkuaiyun.com/weixin_43922901/article/details/102602557

前言

参考文献从论文本身出发进行分析， 算出了Transformer参数量，但是也需要从源码实现来进行分析

Transformer 源码

class ScaledDotProductAttention(nn.Module):
    def __init__(self):
        super(ScaledDotProductAttention, self).__init__()

    def forward(self, Q, K, V, attn_mask):
        '''
        Q: [batch_size, n_heads, len_q, d_k]
        K: [batch_size, n_heads, len_k, d_k]
        V: [batch_size, n_heads, len_v(=len_k), d_v]
        attn_mask: [batch_size, n_heads, seq_len, seq_len]
        '''
        scores = torch.matmul(Q, K.transpose(-1, -2)) / np.sqrt(d_k)  # scores : [batch_size, n_heads, len_q, len_k]
        #scores.masked_fill_(attn_mask, -1e9)  # Fills elements of self tensor with value where mask is True.

        attn = nn.Softmax(dim=-1)(scores)
        context = torch.matmul(attn, V)  # [batch_size, n_heads, len_q, d_v]
        return context, attn


class MultiHeadAttention(nn.Module):
    def __init__(self):
        super(MultiHeadAttention, self).__init__()
        self.W_Q = nn.Linear(d_model, d_k * n_heads, bias=False)
        self.W_K = nn.Linear(d_model, d_k * n_heads, bias=False)
        self.W_V = nn.Linear(d_model, d_v * n_heads, bias=False)
        self.fc = nn.Linear(n_heads * d_v, d_model, bias=False)

    def forward(self, input_Q, input_K, input_V, attn_mask):
        '''
        input_Q: [batch_size, len_q, d_model]
        input_K: [batch_size, len_k, d_model]
        input_V: [batch_size, len_v(=len_k), d_model]
        attn_mask: [batch_size, seq_len, seq_len]
        '''
        residual, batch_size = input_Q, input_Q.size(0)
        # (B, S, D) -proj-> (B, S, D_new) -split-> (B, S, H, W) -trans-> (B, H, S, W)
        Q = self.W_Q(input_Q).view(batch_size, -1, n_heads, d_k).transpose(1, 2)  # Q: [batch_size, n_heads, len_q, d_k]
        K = self.W_K(input_K).view(batch_size, -1, n_heads, d_k).transpose(1, 2)  # K: [batch_size, n_heads, len_k, d_k]
        V = self.W_V(input_V).view(batch_size, -1, n_heads, d_v).transpose(1,
                                                                           2)  # V: [batch_size, n_heads, len_v(=len_k), d_v]

        attn_mask = attn_mask.unsqueeze(1).repeat(1, n_heads, 1,
                                                  1)  # attn_mask : [batch_size, n_heads, seq_len, seq_len]

        # context: [batch_size, n_heads, len_q, d_v], attn: [batch_size, n_heads, len_q, len_k]
        context, attn = ScaledDotProductAttention()(Q, K, V, attn_mask)
        context = context.transpose(1, 2).reshape(batch_size, -1,
                                                  n_heads * d_v)  # context: [batch_size, len_q, n_heads * d_v]
        output = self.fc(context)  # [batch_size, len_q, d_model]
        return nn.LayerNorm(d_model).cuda()(output + residual), attn

要点

• 总共参数 是四个线性层 （代表Q K V 参数矩阵 和 论文中的前馈层）参数量为 4 * H * H
• 一般self attention hidden维度和上一层的维度相同 （在这里即768维）
• 是先进行线性转换 然后 再进行分头 然后做QKV attention 计算 最后
• 分多头直接采用view 即可
• 最后的前馈层也是 一个出入维度相同的层