动手学深度学习PyTorch版-Transformer

Transformer

import os
import math
import numpy as np
import torch 
import torch.nn as nn
import torch.nn.functional as F
import sys
sys.path.append('/home/kesci/input/d2len9900')
import d2l

def SequenceMask(X, X_len,value=-1e6):
    maxlen = X.size(1)
    X_len = X_len.to(X.device)
    #print(X.size(),torch.arange((maxlen),dtype=torch.float)[None, :],'\n',X_len[:, None] )
    mask = torch.arange((maxlen), dtype=torch.float, device=X.device)
    mask = mask[None, :] < X_len[:, None]
    #print(mask)
    X[~mask]=value
    return X

def masked_softmax(X, valid_length):
    # X: 3-D tensor, valid_length: 1-D or 2-D tensor
    softmax = nn.Softmax(dim=-1)
    if valid_length is None:
        return softmax(X)
    else:
        shape = X.shape
        if valid_length.dim() == 1:
            try:
                valid_length = torch.FloatTensor(valid_length.numpy().repeat(shape[1], axis=0))#[2,2,3,3]
            except:
                valid_length = torch.FloatTensor(valid_length.cpu().numpy().repeat(shape[1], axis=0))#[2,2,3,3]
        else:
            valid_length = valid_length.reshape((-1,))
        # fill masked elements with a large negative, whose exp is 0
        X = SequenceMask(X.reshape((-1, shape[-1])), valid_length)
 
        return softmax(X).reshape(shape)

# Save to the d2l package.
class DotProductAttention(nn.Module): 
    def __init__(self, dropout, **kwargs):
        super(DotProductAttention, self).__init__(**kwargs)
        self.dropout = nn.Dropout(dropout)

    # query: (batch_size, #queries, d)
    # key: (batch_size, #kv_pairs, d)
    # value: (batch_size, #kv_pairs, dim_v)
    # valid_length: either (batch_size, ) or (batch_size, xx)
    def forward(self, query, key, value, valid_length=None):
        d = query.shape[-1]
        # set transpose_b=True to swap the last two dimensions of key
        scores = torch.bmm(query, key.transpose(1,2)) / math.sqrt(d)
        attention_weights = self.dropout(masked_softmax(scores, valid_length))
        return torch.bmm(attention_weights, value)

多头注意力层

class MultiHeadAttention(nn.Module):
    def __init__(self, input_size, hidden_size, num_heads, dropout, **kwargs):
        super(MultiHeadAttention, self).__init__(**kwargs)
        self.num_heads = num_heads
        self.attention = DotProductAttention(dropout)
        self.W_q = nn.Linear(input_size, hidden_size, bias=False)
        self.W_k = nn.Linear(input_size, hidden_size, bias=False)
        self.W_v = nn.Linear(input_size, hidden_size, bias=False)
        self.W_o = nn.Linear(hidden_size, hidden_size, bias=False)
    
    def forward(self, query, key, value, valid_length):
        # query, key, and value shape: (batch_size, seq_len, dim),
        # where seq_len is the length of input sequence
        # valid_length shape is either (batch_size, )
        # or (batch_size, seq_len).

        # Project and transpose query, key, and value from
        # (batch_size, seq_len, hidden_size * num_heads) to
        # (batch_size * num_heads, seq_len, hidden_size).
        
        query = transpose_qkv(self.W_q(query), self.num_heads)
        key = transpose_qkv(self.W_k(key), self.num_heads)
        value = transpose_qkv(self.W_v(value), self.num_heads)
        
        if valid_length is not None:
            # Copy valid_length by num_heads times
            device = valid_length.device
            valid_length = valid_length.cpu().numpy() if valid_length.is_cuda else valid_length.numpy()
            if valid_length.ndim == 1:
                valid_length = torch.FloatTensor(np.tile(valid_length, self.num_heads))
            else:
                valid_length = torch.FloatTensor(np.tile(valid_length, (self.num_heads,1)))

            valid_length = valid_length.to(device)
            
        output = self.attention