mirror of
https://github.com/zebrajr/pytorch.git
synced 2025-12-06 12:20:52 +01:00
113 lines
4.0 KiB
Python
113 lines
4.0 KiB
Python
import torch
|
|
from torch.nn.parameter import Parameter
|
|
|
|
from .module import Module
|
|
|
|
|
|
class Embedding(Module):
|
|
r"""A simple lookup table that stores embeddings of a fixed dictionary and size.
|
|
|
|
This module is often used to store word embeddings and retrieve them using indices.
|
|
The input to the module is a list of indices, and the output is the corresponding
|
|
word embeddings.
|
|
|
|
Args:
|
|
num_embeddings (int): size of the dictionary of embeddings
|
|
embedding_dim (int): the size of each embedding vector
|
|
padding_idx (int, optional): If given, pads the output with zeros whenever it encounters the index.
|
|
max_norm (float, optional): If given, will renormalize the embeddings to always have a norm lesser than this
|
|
norm_type (float, optional): The p of the p-norm to compute for the max_norm option
|
|
scale_grad_by_freq (boolean, optional): if given, this will scale gradients by the frequency of
|
|
the words in the mini-batch.
|
|
|
|
Attributes:
|
|
weight (Tensor): the learnable weights of the module of shape (num_embeddings, embedding_dim)
|
|
|
|
Shape:
|
|
- Input: LongTensor `(N, W)`, N = mini-batch, W = number of indices to extract per mini-batch
|
|
- Output: `(N, W, embedding_dim)`
|
|
|
|
Examples::
|
|
|
|
>>> # an Embedding module containing 10 tensors of size 3
|
|
>>> embedding = nn.Embedding(10, 3)
|
|
>>> # a batch of 2 samples of 4 indices each
|
|
>>> input = Variable(torch.LongTensor([[1,2,4,5],[4,3,2,9]]))
|
|
>>> embedding(input)
|
|
|
|
Variable containing:
|
|
(0 ,.,.) =
|
|
-1.0822 1.2522 0.2434
|
|
0.8393 -0.6062 -0.3348
|
|
0.6597 0.0350 0.0837
|
|
0.5521 0.9447 0.0498
|
|
|
|
(1 ,.,.) =
|
|
0.6597 0.0350 0.0837
|
|
-0.1527 0.0877 0.4260
|
|
0.8393 -0.6062 -0.3348
|
|
-0.8738 -0.9054 0.4281
|
|
[torch.FloatTensor of size 2x4x3]
|
|
|
|
>>> # example with padding_idx
|
|
>>> embedding = nn.Embedding(10, 3, padding_idx=0)
|
|
>>> input = Variable(torch.LongTensor([[0,2,0,5]]))
|
|
>>> embedding(input)
|
|
|
|
Variable containing:
|
|
(0 ,.,.) =
|
|
0.0000 0.0000 0.0000
|
|
0.3452 0.4937 -0.9361
|
|
0.0000 0.0000 0.0000
|
|
0.0706 -2.1962 -0.6276
|
|
[torch.FloatTensor of size 1x4x3]
|
|
|
|
"""
|
|
|
|
def __init__(self, num_embeddings, embedding_dim, padding_idx=None,
|
|
max_norm=None, norm_type=2, scale_grad_by_freq=False,
|
|
sparse=False):
|
|
super(Embedding, self).__init__()
|
|
self.num_embeddings = num_embeddings
|
|
self.embedding_dim = embedding_dim
|
|
self.padding_idx = padding_idx
|
|
self.max_norm = max_norm
|
|
self.norm_type = norm_type
|
|
self.scale_grad_by_freq = scale_grad_by_freq
|
|
self.weight = Parameter(torch.Tensor(num_embeddings, embedding_dim))
|
|
self.sparse = sparse
|
|
|
|
self.reset_parameters()
|
|
|
|
def reset_parameters(self):
|
|
self.weight.data.normal_(0, 1)
|
|
if self.padding_idx is not None:
|
|
self.weight.data[self.padding_idx].fill_(0)
|
|
|
|
def forward(self, input):
|
|
padding_idx = self.padding_idx
|
|
if padding_idx is None:
|
|
padding_idx = -1
|
|
return self._backend.Embedding(
|
|
padding_idx, self.max_norm, self.norm_type,
|
|
self.scale_grad_by_freq, self.sparse
|
|
)(input, self.weight)
|
|
|
|
def __repr__(self):
|
|
s = '{name}({num_embeddings}, {embedding_dim}'
|
|
if self.padding_idx is not None:
|
|
s += ', padding_idx={padding_idx}'
|
|
if self.max_norm is not None:
|
|
s += ', max_norm={max_norm}'
|
|
if self.norm_type != 2:
|
|
s += ', norm_type={norm_type}'
|
|
if self.scale_grad_by_freq is not False:
|
|
s += ', scale_grad_by_freq={scale_grad_by_freq}'
|
|
if self.sparse is not False:
|
|
s += ', sparse=True'
|
|
s += ')'
|
|
return s.format(name=self.__class__.__name__, **self.__dict__)
|
|
|
|
|
|
# TODO: SparseLinear
|