attention代碼

s計算score的方式有以下幾種：

import torch
class Attn(nn.module):
    def __init__(self, method ,hidden_size):
        super(Attn, self).__init__()
        self.method = method
        self.hidden_size = hidden_size
        if self.method not in ['dot', 'general', 'concat']:
            raise ValueError(self.method, "is not an appropriate attention method.")
        self.hidden_size = hidden_size
        if self.method == 'general':
            self.attn = nn.Linear(self.hidden_size, hidden_size)
        elif self.method == 'concat':
            self.attn = nn.Linear(self.hidden_size * 2, hidden_size)
            self.v = nn.Parameter(torch.FloatTensor(hidden_size))
    def dot_score(self, hidden, encoder_outputs):
        return torch.sum(hidden*encoder_outputs, dim=2)
    def general_score(self, hidden, encoder_outputs):
        return torch.sum(hidden*self.attn(encoder_outputs), dim=2)
    def concat_score(self, hidden, encoder_outputs):
        energy = self.attn(torc.cat(hidden.expand(encoder_outputs.size(0),-1,-1), encoder_outputs)).tanh()
        return torch.sum(self.v * energy, dim=2)
    def forward(self, hidden, encoder_outputs):
        if self.method == 'general':
            attn_energies = self.general_score(hidden, encoder_outputs)
        elif self.method == 'concat':
            attn_energies = self.concat_score(hidden, encoder_outputs)
        elif self.method == 'dot':
            attn_energies = self.dot_score(hidden, encoder_outputs)

            # Transpose max_length and batch_size dimensions
        attn_energies = attn_energies.t()

        # Return the softmax normalized probability scores (with added dimension)
        return F.softmax(attn_energies, dim=1).unsqueeze(1)
#在LuongAttnDecoderRNN中使用attn:
    rnn_output, hidden = self.gru(embedded, last_hidden)
    attn_weights = self.attn(rnn_output, encoder_outputs)
    context = attn_weights.bmm(encoder_outputs.transpose(0, 1))
    #[batch, 1, hidden]
    context = context.squeeze(1)#去除size爲1的維度
    #[batch, hidden]
    concat_input = torch.cat((rnn_output, context), 1)
    concat_output = torch.tanh(self.concat(concat_input))
    output = self.out(concat_output)
    output = F.softmax(output, dim=1)

bert中的attn

借鑑別人博客明白的

class BertSelfAttention(nn.Module):
    def __init__(self, config):
        super(BertSelfAttention, self).__init__()
        if config.hidden_size % config.num_attention_heads != 0:
            raise ValueError(
                "The hidden size (%d) is not a multiple of the number of attention "
                "heads (%d)" % (config.hidden_size, config.num_attention_heads))
        self.output_attentions = config.output_attentions

        self.num_attention_heads = config.num_attention_heads
        self.attention_head_size = int(config.hidden_size / config.num_attention_heads)
        self.all_head_size = self.num_attention_heads * self.attention_head_size

        self.query = nn.Linear(config.hidden_size, self.all_head_size)
        self.key = nn.Linear(config.hidden_size, self.all_head_size)
        self.value = nn.Linear(config.hidden_size, self.all_head_size)

        self.dropout = nn.Dropout(config.attention_probs_dropout_prob)

    def transpose_for_scores(self, x):
        new_x_shape = x.size()[:-1] + (self.num_attention_heads, self.attention_head_size)
        x = x.view(*new_x_shape)
        return x.permute(0, 2, 1, 3)

    def forward(self, hidden_states, attention_mask, head_mask=None):
        mixed_query_layer = self.query(hidden_states)
        mixed_key_layer = self.key(hidden_states)
        mixed_value_layer = self.value(hidden_states)

        query_layer = self.transpose_for_scores(mixed_query_layer)
        key_layer = self.transpose_for_scores(mixed_key_layer)
        value_layer = self.transpose_for_scores(mixed_value_layer)

        # Take the dot product between "query" and "key" to get the raw attention scores.
        attention_scores = torch.matmul(query_layer, key_layer.transpose(-1, -2))
        attention_scores = attention_scores / math.sqrt(self.attention_head_size)
        # Apply the attention mask is (precomputed for all layers in BertModel forward() function)
        attention_scores = attention_scores + attention_mask

        # Normalize the attention scores to probabilities.
        attention_probs = nn.Softmax(dim=-1)(attention_scores)

        # This is actually dropping out entire tokens to attend to, which might
        # seem a bit unusual, but is taken from the original Transformer paper.
        attention_probs = self.dropout(attention_probs)

        # Mask heads if we want to
        if head_mask is not None:
            attention_probs = attention_probs * head_mask

        context_layer = torch.matmul(attention_probs, value_layer)

        context_layer = context_layer.permute(0, 2, 1, 3).contiguous()
        new_context_layer_shape = context_layer.size()[:-2] + (self.all_head_size,)
        context_layer = context_layer.view(*new_context_layer_shape)

        outputs = (context_layer, attention_probs) if self.output_attentions else (context_layer,)
        return outputs
        ```