sg] d dl mZ d dlZd dlmZ d dlmZmZ d dlm Z ddl
m Z dd gZ G d
de Z
G d d e Zy) )OptionalN)Tensor)
functionalinit) Parameter )Module Embedding EmbeddingBagc , e Zd ZU dZg dZeed< eed< ee ed< ee ed< eed< e ed< e
ed < e ed
< e ed < ddededee dee dede d e d
ee
de dd f fd
Z ddZ ddZ
de
de
fdZdefdZe dd Z xZS )r
a 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 specified, the entries at :attr:`padding_idx` do not contribute to the gradient;
therefore, the embedding vector at :attr:`padding_idx` is not updated during training,
i.e. it remains as a fixed "pad". For a newly constructed Embedding,
the embedding vector at :attr:`padding_idx` will default to all zeros,
but can be updated to another value to be used as the padding vector.
max_norm (float, optional): If given, each embedding vector with norm larger than :attr:`max_norm`
is renormalized to have norm :attr:`max_norm`.
norm_type (float, optional): The p of the p-norm to compute for the :attr:`max_norm` option. Default ``2``.
scale_grad_by_freq (bool, optional): If given, this will scale gradients by the inverse of frequency of
the words in the mini-batch. Default ``False``.
sparse (bool, optional): If ``True``, gradient w.r.t. :attr:`weight` matrix will be a sparse tensor.
See Notes for more details regarding sparse gradients.
Attributes:
weight (Tensor): the learnable weights of the module of shape (num_embeddings, embedding_dim)
initialized from :math:`\mathcal{N}(0, 1)`
Shape:
- Input: :math:`(*)`, IntTensor or LongTensor of arbitrary shape containing the indices to extract
- Output: :math:`(*, H)`, where `*` is the input shape and :math:`H=\text{embedding\_dim}`
.. note::
Keep in mind that only a limited number of optimizers support
sparse gradients: currently it's :class:`optim.SGD` (`CUDA` and `CPU`),
:class:`optim.SparseAdam` (`CUDA` and `CPU`) and :class:`optim.Adagrad` (`CPU`)
.. note::
When :attr:`max_norm` is not ``None``, :class:`Embedding`'s forward method will modify the
:attr:`weight` tensor in-place. Since tensors needed for gradient computations cannot be
modified in-place, performing a differentiable operation on ``Embedding.weight`` before
calling :class:`Embedding`'s forward method requires cloning ``Embedding.weight`` when
:attr:`max_norm` is not ``None``. For example::
n, d, m = 3, 5, 7
embedding = nn.Embedding(n, d, max_norm=1.0)
W = torch.randn((m, d), requires_grad=True)
idx = torch.tensor([1, 2])
a = embedding.weight.clone() @ W.t() # weight must be cloned for this to be differentiable
b = embedding(idx) @ W.t() # modifies weight in-place
out = (a.unsqueeze(0) + b.unsqueeze(1))
loss = out.sigmoid().prod()
loss.backward()
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 = torch.LongTensor([[1, 2, 4, 5], [4, 3, 2, 9]])
>>> # xdoctest: +IGNORE_WANT("non-deterministic")
>>> embedding(input)
tensor([[[-0.0251, -1.6902, 0.7172],
[-0.6431, 0.0748, 0.6969],
[ 1.4970, 1.3448, -0.9685],
[-0.3677, -2.7265, -0.1685]],
[[ 1.4970, 1.3448, -0.9685],
[ 0.4362, -0.4004, 0.9400],
[-0.6431, 0.0748, 0.6969],
[ 0.9124, -2.3616, 1.1151]]])
>>> # example with padding_idx
>>> embedding = nn.Embedding(10, 3, padding_idx=0)
>>> input = torch.LongTensor([[0, 2, 0, 5]])
>>> embedding(input)
tensor([[[ 0.0000, 0.0000, 0.0000],
[ 0.1535, -2.0309, 0.9315],
[ 0.0000, 0.0000, 0.0000],
[-0.1655, 0.9897, 0.0635]]])
>>> # example of changing `pad` vector
>>> padding_idx = 0
>>> embedding = nn.Embedding(3, 3, padding_idx=padding_idx)
>>> embedding.weight
Parameter containing:
tensor([[ 0.0000, 0.0000, 0.0000],
[-0.7895, -0.7089, -0.0364],
[ 0.6778, 0.5803, 0.2678]], requires_grad=True)
>>> with torch.no_grad():
... embedding.weight[padding_idx] = torch.ones(3)
>>> embedding.weight
Parameter containing:
tensor([[ 1.0000, 1.0000, 1.0000],
[-0.7895, -0.7089, -0.0364],
[ 0.6778, 0.5803, 0.2678]], requires_grad=True)
)num_embeddings
embedding_dim padding_idxmax_norm norm_typescale_grad_by_freqsparser
r r r r r weightfreezer N_weight_freezereturnc |
| d} t
| || _ || _ |F|dkD r|| j k s2J d |dk r&|| j k\ sJ d | j |z }|| _ || _ || _ || _ |At t j ||ffi | | | _ | j || _ y t |j ||gk( sJ d t || | _ || _ y )Ndevicedtyper z)Padding_idx must be within num_embeddings)
requires_grad?Shape of weight does not match num_embeddings and embedding_dim)super__init__r
r r r r r r torchemptyr reset_parameterslistshaper )selfr
r r r r r r r r r r factory_kwargs __class__s J/var/www/html/venv/lib/python3.12/site-packages/torch/nn/modules/sparse.pyr zEmbedding.__init__ s< %+U;
, * "Q $"5"55?>?5 q D$7$7#77?>?7 " 1 1K ? &
""4 ?# ^] ;N~N")kDK
! ! #
& +
Q Q
Q $Gw;GDK c b t j | j | j y Nr normal_r _fill_padding_idx_with_zeror& s r) r# zEmbedding.reset_parameters T[[! ((*r* c | j Ft j 5 | j | j j d d d d y y # 1 sw Y y xY wNr r r! no_gradr fill_r0 s r) r/ z%Embedding._fill_padding_idx_with_zero S '
7 D , ,-33A6
7
7 (
7
7 )AA inputc t j || j | j | j | j
| j | j S r, )F embeddingr r r r r r )r& r9 s r) forwardzEmbedding.forward sD {{ KK MM NN # # KK
r* c d}| j |dz
}| j |dz
}| j dk7 r|dz
}| j dur|dz
}| j dur|dz
} |j
d i | j S )
N!{num_embeddings}, {embedding_dim}, padding_idx={padding_idx}, max_norm={max_norm} , norm_type={norm_type}F), scale_grad_by_freq={scale_grad_by_freq}z
, sparse=True )r r r r r format__dict__)r& ss r)
extra_reprzEmbedding.extra_repr s / '
. .A == $
( (A >>Q
* *A " "% /
< >> # FloatTensor containing pretrained weights
>>> weight = torch.FloatTensor([[1, 2.3, 3], [4, 5.1, 6.3]])
>>> embedding = nn.Embedding.from_pretrained(weight)
>>> # Get embeddings for index 1
>>> input = torch.LongTensor([1])
>>> # xdoctest: +IGNORE_WANT("non-deterministic")
>>> embedding(input)
tensor([[ 4.0000, 5.1000, 6.3000]])
rB 4Embeddings parameter is expected to be 2-dimensional) r
r r r r r r r r )dimr% ) cls
embeddingsr r r r r r rowscolsr< s r) from_pretrainedzEmbedding.from_pretrained sb L
NN ! B A B ! %%
d # 1
r* ) NN @FFNFNNr N)TNNrR FF)__name__
__module__ __qualname____doc__
__constants__int__annotations__r floatboolr r r# r/ r= strrI classmethodrQ
__classcell__r( s @r) r
r
s1 _BM # uo N L L &*$( #( $( - - - c] -
5/ -
- !- - &!- -
- ^+7
V
)C ) 3 3r* c e Zd ZU dZg dZeed< eed< ee ed< eed< e ed< e
ed< e ed < e ed
< e ed < ee ed < ddededee dede d e d
e dee
d e d ee dd
f fd
Z d dZ
d dZ d de
dee
dee
de
fdZde fdZe d de
de dee dede d e d
e d e d ee dd fd Z xZS ) r aL Compute sums or means of 'bags' of embeddings, without instantiating the intermediate embeddings.
For bags of constant length, no :attr:`per_sample_weights`, no indices equal to :attr:`padding_idx`,
and with 2D inputs, this class
* with ``mode="sum"`` is equivalent to :class:`~torch.nn.Embedding` followed by ``torch.sum(dim=1)``,
* with ``mode="mean"`` is equivalent to :class:`~torch.nn.Embedding` followed by ``torch.mean(dim=1)``,
* with ``mode="max"`` is equivalent to :class:`~torch.nn.Embedding` followed by ``torch.max(dim=1)``.
However, :class:`~torch.nn.EmbeddingBag` is much more time and memory efficient than using a chain of these
operations.
EmbeddingBag also supports per-sample weights as an argument to the forward
pass. This scales the output of the Embedding before performing a weighted
reduction as specified by ``mode``. If :attr:`per_sample_weights` is passed, the
only supported ``mode`` is ``"sum"``, which computes a weighted sum according to
:attr:`per_sample_weights`.
Args:
num_embeddings (int): size of the dictionary of embeddings
embedding_dim (int): the size of each embedding vector
max_norm (float, optional): If given, each embedding vector with norm larger than :attr:`max_norm`
is renormalized to have norm :attr:`max_norm`.
norm_type (float, optional): The p of the p-norm to compute for the :attr:`max_norm` option. Default ``2``.
scale_grad_by_freq (bool, optional): if given, this will scale gradients by the inverse of frequency of
the words in the mini-batch. Default ``False``.
Note: this option is not supported when ``mode="max"``.
mode (str, optional): ``"sum"``, ``"mean"`` or ``"max"``. Specifies the way to reduce the bag.
``"sum"`` computes the weighted sum, taking :attr:`per_sample_weights`
into consideration. ``"mean"`` computes the average of the values
in the bag, ``"max"`` computes the max value over each bag.
Default: ``"mean"``
sparse (bool, optional): if ``True``, gradient w.r.t. :attr:`weight` matrix will be a sparse tensor. See
Notes for more details regarding sparse gradients. Note: this option is not
supported when ``mode="max"``.
include_last_offset (bool, optional): if ``True``, :attr:`offsets` has one additional element, where the last element
is equivalent to the size of `indices`. This matches the CSR format.
padding_idx (int, optional): If specified, the entries at :attr:`padding_idx` do not contribute to the
gradient; therefore, the embedding vector at :attr:`padding_idx` is not updated
during training, i.e. it remains as a fixed "pad". For a newly constructed
EmbeddingBag, the embedding vector at :attr:`padding_idx` will default to all
zeros, but can be updated to another value to be used as the padding vector.
Note that the embedding vector at :attr:`padding_idx` is excluded from the
reduction.
Attributes:
weight (Tensor): the learnable weights of the module of shape `(num_embeddings, embedding_dim)`
initialized from :math:`\mathcal{N}(0, 1)`.
Examples::
>>> # an EmbeddingBag module containing 10 tensors of size 3
>>> embedding_sum = nn.EmbeddingBag(10, 3, mode='sum')
>>> # a batch of 2 samples of 4 indices each
>>> input = torch.tensor([1, 2, 4, 5, 4, 3, 2, 9], dtype=torch.long)
>>> offsets = torch.tensor([0, 4], dtype=torch.long)
>>> # xdoctest: +IGNORE_WANT("non-deterministic")
>>> embedding_sum(input, offsets)
tensor([[-0.8861, -5.4350, -0.0523],
[ 1.1306, -2.5798, -1.0044]])
>>> # Example with padding_idx
>>> embedding_sum = nn.EmbeddingBag(10, 3, mode='sum', padding_idx=2)
>>> input = torch.tensor([2, 2, 2, 2, 4, 3, 2, 9], dtype=torch.long)
>>> offsets = torch.tensor([0, 4], dtype=torch.long)
>>> embedding_sum(input, offsets)
tensor([[ 0.0000, 0.0000, 0.0000],
[-0.7082, 3.2145, -2.6251]])
>>> # An EmbeddingBag can be loaded from an Embedding like so
>>> embedding = nn.Embedding(10, 3, padding_idx=2)
>>> embedding_sum = nn.EmbeddingBag.from_pretrained(
embedding.weight,
padding_idx=embedding.padding_idx,
mode='sum')
) r
r r r r moder include_last_offsetr r
r r r r r rb r rc r Nr r c
| | d}
t | || _ || _ || _ || _ || _ |
F|
dkD r|
| j k s2J d |
dk r&|
| j k\ sJ d | j |
z }
|
| _ |7t t j ||ffi |
| _ | j n1t |j ||gk( sJ d t | | _ || _ || _ | | _ y )Nr r z)padding_idx must be within num_embeddingsr )r r r
r r r r r r r! r" r r# r$ r% rb r rc )r& r
r r r r rb r r rc r r r r' r( s r) r zEmbeddingBag.__init__r s7 %+U;
, *
""4 "Q $"5"55?>?5 q D$7$7#77?>?7 " 1 1K ? & ?# ^] ;N~NDK
! ! #
& +
Q Q
Q $G,DK #6 r* c b t j | j | j y r, r- r0 s r) r# z EmbeddingBag.reset_parameters r1 r* c | j Ft j 5 | j | j j d d d d y y # 1 sw Y y xY wr3 r4 r0 s r) r/ z(EmbeddingBag._fill_padding_idx_with_zero r7 r8 r9 offsetsper_sample_weightsc
t j || j || j | j | j
| j | j || j | j S )a Forward pass of EmbeddingBag.
Args:
input (Tensor): Tensor containing bags of indices into the embedding matrix.
offsets (Tensor, optional): Only used when :attr:`input` is 1D. :attr:`offsets` determines
the starting index position of each bag (sequence) in :attr:`input`.
per_sample_weights (Tensor, optional): a tensor of float / double weights, or None
to indicate all weights should be taken to be ``1``. If specified, :attr:`per_sample_weights`
must have exactly the same shape as input and is treated as having the same
:attr:`offsets`, if those are not ``None``. Only supported for ``mode='sum'``.
Returns:
Tensor output shape of `(B, embedding_dim)`.
.. note::
A few notes about ``input`` and ``offsets``:
- :attr:`input` and :attr:`offsets` have to be of the same type, either int or long
- If :attr:`input` is 2D of shape `(B, N)`, it will be treated as ``B`` bags (sequences)
each of fixed length ``N``, and this will return ``B`` values aggregated in a way
depending on the :attr:`mode`. :attr:`offsets` is ignored and required to be ``None`` in this case.
- If :attr:`input` is 1D of shape `(N)`, it will be treated as a concatenation of
multiple bags (sequences). :attr:`offsets` is required to be a 1D tensor containing the
starting index positions of each bag in :attr:`input`. Therefore, for :attr:`offsets` of shape `(B)`,
:attr:`input` will be viewed as having ``B`` bags. Empty bags (i.e., having 0-length) will have
returned vectors filled by zeros.
)
r;
embedding_bagr r r r rb r rc r )r& r9 rg rh s r) r= zEmbeddingBag.forward s] H KK MM NN # # II KK $ $
r* c < d}| j |dz
}| j dk7 r|dz
}| j dur|dz
}|dz
}| j |dz
} |j d i | j
j
D ci c] \ }}|t | c}}S c c}}w )
Nr? rA rB rC FrD z
, mode={mode}r@ rE )r r r r rF rG itemsrepr)r& rH kvs r) rI zEmbeddingBag.extra_repr s / == $
( (A >>Q
* *A " "% /
< >> # FloatTensor containing pretrained weights
>>> weight = torch.FloatTensor([[1, 2.3, 3], [4, 5.1, 6.3]])
>>> embeddingbag = nn.EmbeddingBag.from_pretrained(weight)
>>> # Get embeddings for index 1
>>> input = torch.LongTensor([[1, 0]])
>>> # xdoctest: +IGNORE_WANT("non-deterministic")
>>> embeddingbag(input)
tensor([[ 2.5000, 3.7000, 4.6500]])
rB rK )
r
r r r r r rb r rc r )rL r% r r )
rM rN r r r r rb r rc r rO rP embeddingbags
r) rQ z EmbeddingBag.from_pretrained su P
NN ! B A B ! %%
d 1 3#
17J )r* )
NrR FmeanFNFNNNrS )NN)TNrR Frr FFN)rT rU rV rW rX rY rZ r r[ r\ r r] r r# r/ r= rI r^ rQ r_ r` s @r) r r
s KZ
M uo N
I L # %) #( $($)%).7.7 .7 5/ .7
.7 !
.7 .7 .7 &!.7 ".7 c].7
.7`+7 %)/3 0
0
&!0
%V , 0
0
d JC J $( #( $)%)7 7 7 5/ 7
7 !
7 7 7 "7 c]7
7 7 r* )typingr r! r torch.nnr r; r torch.nn.parameterr moduler __all__r
r rE r* r) rx s@ * (
'{ {|U 6 U r*