multi_head_attention_torch.ipynb

Kernel: Python 3.6.7 64-bit ('base': conda)

Please find jax implementation of this notebook here: https://colab.research.google.com/github/probml/pyprobml/blob/master/notebooks/book1/15/multi_head_attention_jax.ipynb

Multi-head attention.

We show how to multi-head attention. Based on sec 10.5 of http://d2l.ai/chapter_attention-mechanisms/multihead-attention.html.

import numpy as np
import matplotlib.pyplot as plt

np.random.seed(seed=1)
import math
import collections

try:
    import torch
except ModuleNotFoundError:
    %pip install -qq torch
    import torch
from torch import nn
from torch.nn import functional as F

!mkdir figures # for saving plots

Implementation

Utility functions.

def transpose_qkv(X, num_heads):
    # Shape of input `X`:
    # (`batch_size`, no. of queries or key-value pairs, `num_hiddens`).
    # Shape of output `X`:
    # (`batch_size`, no. of queries or key-value pairs, `num_heads`,
    # `num_hiddens` / `num_heads`)
    X = X.reshape(X.shape[0], X.shape[1], num_heads, -1)

    # Shape of output `X`:
    # (`batch_size`, `num_heads`, no. of queries or key-value pairs,
    # `num_hiddens` / `num_heads`)
    X = X.permute(0, 2, 1, 3)

    # Shape of `output`:
    # (`batch_size` * `num_heads`, no. of queries or key-value pairs,
    # `num_hiddens` / `num_heads`)
    return X.reshape(-1, X.shape[2], X.shape[3])


# @save
def transpose_output(X, num_heads):
    """Reverse the operation of `transpose_qkv`"""
    X = X.reshape(-1, num_heads, X.shape[1], X.shape[2])
    X = X.permute(0, 2, 1, 3)
    return X.reshape(X.shape[0], X.shape[1], -1)

Main function.

def sequence_mask(X, valid_len, value=0):
    """Mask irrelevant entries in sequences."""
    maxlen = X.size(1)
    mask = torch.arange((maxlen), dtype=torch.float32, device=X.device)[None, :] < valid_len[:, None]
    X[~mask] = value
    return X


def masked_softmax(X, valid_lens):
    """Perform softmax operation by masking elements on the last axis."""
    # `X`: 3D tensor, `valid_lens`: 1D or 2D tensor
    if valid_lens is None:
        return nn.functional.softmax(X, dim=-1)
    else:
        shape = X.shape
        if valid_lens.dim() == 1:
            valid_lens = torch.repeat_interleave(valid_lens, shape[1])
        else:
            valid_lens = valid_lens.reshape(-1)
        # On the last axis, replace masked elements with a very large negative
        # value, whose exponentiation outputs 0
        X = sequence_mask(X.reshape(-1, shape[-1]), valid_lens, value=-1e6)
        return nn.functional.softmax(X.reshape(shape), dim=-1)

class DotProductAttention(nn.Module):
    """Scaled dot product attention."""

    def __init__(self, dropout, **kwargs):
        super(DotProductAttention, self).__init__(**kwargs)
        self.dropout = nn.Dropout(dropout)

    # Shape of `queries`: (`batch_size`, no. of queries, `d`)
    # Shape of `keys`: (`batch_size`, no. of key-value pairs, `d`)
    # Shape of `values`: (`batch_size`, no. of key-value pairs, value
    # dimension)
    # Shape of `valid_lens`: (`batch_size`,) or (`batch_size`, no. of queries)
    def forward(self, queries, keys, values, valid_lens=None):
        d = queries.shape[-1]
        # Set `transpose_b=True` to swap the last two dimensions of `keys`
        scores = torch.bmm(queries, keys.transpose(1, 2)) / math.sqrt(d)
        self.attention_weights = masked_softmax(scores, valid_lens)
        return torch.bmm(self.dropout(self.attention_weights), values)

class MultiHeadAttention(nn.Module):
    def __init__(self, key_size, query_size, value_size, num_hiddens, num_heads, dropout, bias=False, **kwargs):
        super(MultiHeadAttention, self).__init__(**kwargs)
        self.num_heads = num_heads
        self.attention = DotProductAttention(dropout)
        self.W_q = nn.Linear(query_size, num_hiddens, bias=bias)
        self.W_k = nn.Linear(key_size, num_hiddens, bias=bias)
        self.W_v = nn.Linear(value_size, num_hiddens, bias=bias)
        self.W_o = nn.Linear(num_hiddens, num_hiddens, bias=bias)

    def forward(self, queries, keys, values, valid_lens):
        # Shape of `queries`, `keys`, or `values`:
        # (`batch_size`, no. of queries or key-value pairs, `num_hiddens`)
        # Shape of `valid_lens`:
        # (`batch_size`,) or (`batch_size`, no. of queries)
        # After transposing, shape of output `queries`, `keys`, or `values`:
        # (`batch_size` * `num_heads`, no. of queries or key-value pairs,
        # `num_hiddens` / `num_heads`)
        queries = transpose_qkv(self.W_q(queries), self.num_heads)
        keys = transpose_qkv(self.W_k(keys), self.num_heads)
        values = transpose_qkv(self.W_v(values), self.num_heads)

        if valid_lens is not None:
            # On axis 0, copy the first item (scalar or vector) for
            # `num_heads` times, then copy the next item, and so on
            valid_lens = torch.repeat_interleave(valid_lens, repeats=self.num_heads, dim=0)

        # Shape of `output`: (`batch_size` * `num_heads`, no. of queries,
        # `num_hiddens` / `num_heads`)
        output = self.attention(queries, keys, values, valid_lens)

        # Shape of `output_concat`:
        # (`batch_size`, no. of queries, `num_hiddens`)
        output_concat = transpose_output(output, self.num_heads)
        return self.W_o(output_concat)

Example

The shape of the multi-head attention output is (batch_size, num_queries, num_hiddens).

num_hiddens, num_heads = 100, 5
attention = MultiHeadAttention(num_hiddens, num_hiddens, num_hiddens, num_hiddens, num_heads, 0.5)
attention.eval()

MultiHeadAttention(
  (attention): DotProductAttention(
    (dropout): Dropout(p=0.5, inplace=False)
  )
  (W_q): Linear(in_features=100, out_features=100, bias=False)
  (W_k): Linear(in_features=100, out_features=100, bias=False)
  (W_v): Linear(in_features=100, out_features=100, bias=False)
  (W_o): Linear(in_features=100, out_features=100, bias=False)
)

batch_size, num_queries, num_kvpairs, valid_lens = 2, 4, 6, torch.tensor([3, 2])
X = torch.ones((batch_size, num_queries, num_hiddens))
Y = torch.ones((batch_size, num_kvpairs, num_hiddens))
attention(X, Y, Y, valid_lens).shape

torch.Size([2, 4, 100])