˲j`ddlmZddlZddlmZddlmZmZddlm Z ddl m Z dd gZ Gd de Z Gd d e ZdS) )OptionalN)Tensor) functionalinit) Parameter)Module Embedding EmbeddingBagcPeZdZUdZgdZeed<eed<eeed<eeed<eed<e ed<e ed <e ed <e ed < ddededeedeedede d e dee de dd ffd Z ddZ ddZ de de fdZdefdZe ddZxZS)r aA 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 rrrrrweightfreezerN@F_weight_freezereturnc 2| | d} t||_||_|B|dkr||jks Jdn&|dkr ||j ks Jd|j|z}||_||_||_||_|>ttj ||ffi| | |_ | n;t|j||gks Jdt|| |_ ||_dS)Ndevicedtyperz)Padding_idx must be within num_embeddings) requires_grad?Shape of weight does not match num_embeddings and embedding_dim)super__init__r rrrrrrtorchemptyrreset_parameterslistshaper)selfr rrrrrrrrrrfactory_kwargs __class__s HC:\Projects\Historical\venv\Lib\site-packages\torch/nn/modules/sparse.pyr!zEmbedding.__init__so%+U;; ,*  "Q$"5555>6555qD$7#7777>877"1K? &  ""4 ?# ^];NN~NN")kDK  ! ! # # # # &&+Q$Gw;GGGDK c`tj|j|dSNrnormal_r_fill_padding_idx_with_zeror's r*r$zEmbedding.reset_parameters, T[!!! ((*****r+c|jStj5|j|jdddddS#1swxYwYdSdSNrrr"no_gradrfill_r1s r*r0z%Embedding._fill_padding_idx_with_zero   ' 7 7 D,-33A666 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 ( '&AAAinputc rtj||j|j|j|j|j|jSr-)F embeddingrrrrrr)r'r:s r*forwardzEmbedding.forwards9{  K   M N  # K   r+cd}|j|dz }|j|dz }|jdkr|dz }|jdur|dz }|jdur|dz }|jd i|jS) 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)rrrrrformat__dict__r'ss r* extra_reprzEmbedding.extra_reprs /   ' . .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]]) rC4Embeddings parameter is expected to be 2-dimensional) r rrrrrrrr)dimr&) cls embeddingsrrrrrrrowscolsr=s r*from_pretrainedzEmbedding.from_pretrainedspL NN   ! ! ! A " ! !% dC#1    r+) NNrFFNFNNrN)TNNrFF)__name__ __module__ __qualname____doc__ __constants__int__annotations__rfloatboolrr!r$r0r>strrK classmethodrS __classcell__r)s@r*r r s__BM#uo NNN LLL LLL &*$(#($(----c] - 5/ -  -!--&!-- ------^++++7777  V        )C ) ) ) ) 333[33333r+ceZdZUdZgdZeed<eed<eeed<eed<e ed<e ed<e ed <e ed <e ed <eeed < ddededeedede d e d e dee d e d eedd ffd Z d dZ d dZ d!de dee dee de fdZde fdZe d"de de deedede d e d e d e d eeddfdZxZS)#r aLCompute 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 rrrrmoderinclude_last_offsetrr rrrrrrcrrdrNrFmeanrrc B| | d} t||_||_||_||_||_| B| dkr| |jks Jdn&| dkr | |j ks Jd|j| z} | |_|;ttj ||ffi| |_ | n8t|j||gks Jdt||_ ||_||_| |_dS)Nrrz)padding_idx must be within num_embeddingsr)r r!r rrrrrrr"r#rr$r%r&rcrrd)r'r rrrrrcrrrdrrrr(r)s r*r!zEmbeddingBag.__init__rso%+U;; ,*  ""4  "Q$"5555>6555qD$7#7777>877"1K? & ?# ^];NN~NNDK  ! ! # # # # &&+Q$G,,DK  #6   r+c`tj|j|dSr-r.r1s r*r$zEmbeddingBag.reset_parametersr2r+c|jStj5|j|jdddddS#1swxYwYdSdSr4r5r1s r*r0z(EmbeddingBag._fill_padding_idx_with_zeror8r9r:offsetsper_sample_weightsc tj||j||j|j|j|j|j||j|j S)aForward 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_bagrrrrrcrrdr)r'r:rirjs r*r>zEmbeddingBag.forwardsMH  K  M N  # I K   $     r+cd}|j|dz }|jdkr|dz }|jdur|dz }|dz }|j|dz }|jd id |jDS) Nr@rBrCrDFrEz , mode={mode}rAc4i|]\}}|t|SrF)repr).0kvs r* z+EmbeddingBag.extra_repr..s$HHH$!Q1d1ggHHHr+rF)rrrrrGrHitemsrIs r*rKzEmbeddingBag.extra_reprs / = $ ( (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]]) rCrM) r rrrrrrcrrdr)rNr&rr) rOrPrrrrrcrrdrrQrR embeddingbags r*rSzEmbeddingBag.from_pretrainedsP NN   ! ! ! A " ! !% ds1 3#    17J )r+) NrFreFNFNNNrT)NN)TNrFreFFN)rUrVrWrXrYrZr[rr\r]rr^r!r$r0r>rKr_rSr`ras@r*r r sKKZ   Muo NNN III LLL# %)#($($)%).7.7.7.75/ .7  .7 ! .7.7.7&!.7".7c].7 .7.7.7.7.7.7`++++7777%)/3 0 0 0 &!0 %V, 0  0 0 0 0 d JC J J J J$(#($)%)77775/ 7  7 ! 777"7c]7 777[77777r+)typingrr"rtorch.nnrr<rtorch.nn.parameterrmoduler __all__r r rFr+r*r|s ********((((((  '{{{{{{{{|UUUUU6UUUUUr+