Name	Size	Mode	Actions
activation.cpython-36.pyc	47635	0644	editdlrm
adaptive.cpython-36.pyc	9725	0644	editdlrm
batchnorm.cpython-36.pyc	31039	0644	editdlrm
channelshuffle.cpython-36.pyc	1901	0644	editdlrm
container.cpython-36.pyc	27970	0644	editdlrm
conv.cpython-36.pyc	57789	0644	editdlrm
distance.cpython-36.pyc	3684	0644	editdlrm
dropout.cpython-36.pyc	10310	0644	editdlrm
flatten.cpython-36.pyc	5813	0644	editdlrm
fold.cpython-36.pyc	12807	0644	editdlrm
instancenorm.cpython-36.pyc	18808	0644	editdlrm
lazy.cpython-36.pyc	11690	0644	editdlrm
linear.cpython-36.pyc	10188	0644	editdlrm
loss.cpython-36.pyc	91465	0644	editdlrm
module.cpython-36.pyc	66530	0644	editdlrm
normalization.cpython-36.pyc	11360	0644	editdlrm
padding.cpython-36.pyc	22217	0644	editdlrm
pixelshuffle.cpython-36.pyc	4398	0644	editdlrm
pooling.cpython-36.pyc	53203	0644	editdlrm
rnn.cpython-36.pyc	44653	0644	editdlrm
sparse.cpython-36.pyc	20956	0644	editdlrm
transformer.cpython-36.pyc	20737	0644	editdlrm
upsampling.cpython-36.pyc	10780	0644	editdlrm
utils.cpython-36.pyc	2528	0644	editdlrm
_functions.cpython-36.pyc	5441	0644	editdlrm
__init__.cpython-36.pyc	5236	0644	editdlrm

3 �Eg�Y�@stdd
lm
Z

ddlZddlmZ
ddlmZ
ddlmZ
ddlm Z
dd lmZ
Gd d�de�ZGdd �d e�Z dS)�)
�OptionalN)
�Tensor)
� Parameter�
)
�Module�)
� functional)
�initcs�eZ
dZUd
ZdddddddgZeeee ee e e ee deeeeee e e e eed d� �f
d d� Zd d�
dd�Zd d�
dd�Zeed�dd�Zed�
dd�Zeddd�
�
Z�ZS)� EmbeddingaeA 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 (boolean, 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=True) 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]]) >>> 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_idx�max_norm� norm_type�scale_grad_by_freq�sparseN�@F) rrr rrrr�_weight�returncs�| | d
�}tt
|�j�
|
|_||_|dk rn|dkrH||jksntd�
�
n&|dkrn||jksdtd�
�
|j|}||_||_||_||_ |dkr�t tj|
|ff
|�
�
|_ |j�
n$t|j�
|
|gks�td�
�
t |�
|_ ||_dS)N)�device�dtyper
z)Padding_idx must be within num_embeddingsz?Shape of weight does not match num_embeddings and embedding_dim)�superr �__init__rr�AssertionErrorr rrrr�torch�empty�weight�reset_parameters�list�shaper)�selfrrr rrrrrrr�factory_kwargs)
� __class__��C/usr/local/lib64/python3.6/site-packages/torch/nn/modules/sparse.pyrxs*

















zEmbedding.__init__)
rc

Cstj
|j�

|j�
dS)
N)r �normal_r�_fill_padding_idx_with_zero)
r r#r#r$r�s

zEmbedding.reset_parametersc

Cs4|jdk r0t
j��
|j|jjd
�

WdQRXdS)Nr
)r r�no_gradr�fill_)
r r#r#r$r&�s


z%Embedding._fill_padding_idx_with_zero)�inputrcCs"tj
|
|j|j|j|j|j|j�S)
N)�
F� embeddingrr rrrr)r r)r#r#r$�forward�s


zEmbedding.forwardc
Csld
}
|jdk r|
d7}
|j
dk r(|
d7}
|jdkr:|
d7}
|jdk rL|
d7}
|jdk r^|
d7}
|
jf|j�
S) Nz!{num_embeddings}, {embedding_dim}z, padding_idx={padding_idx}z, max_norm={max_norm}rz, norm_type={norm_type}Fz), scale_grad_by_freq={scale_grad_by_freq}z , sparse=True)r rrrr�format�__dict__)r �
sr#r#r$� extra_repr�s











zEmbedding.extra_reprTc CsD|
j�d
kst
d�
�
|
j\}} ||| |
|||||d�} || j_| S)a'Creates Embedding instance from given 2-dimensional FloatTensor. Args: embeddings (Tensor): FloatTensor containing weights for the Embedding. First dimension is being passed to Embedding as ``num_embeddings``, second as ``embedding_dim``. freeze (boolean, optional): If ``True``, the tensor does not get updated in the learning process. Equivalent to ``embedding.weight.requires_grad = False``. Default: ``True`` 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". max_norm (float, optional): See module initialization documentation. norm_type (float, optional): See module initialization documentation. Default ``2``. scale_grad_by_freq (boolean, optional): See module initialization documentation. Default ``False``. sparse (bool, optional): See module initialization documentation. Examples:: >>> # 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]) >>> embedding(input) tensor([[ 4.0000, 5.1000, 6.3000]]) rz4Embeddings parameter is expected to be 2-dimensional)rrrr rrrr)�dimrrr� requires_grad)�cls� embeddings�freezer rrrr�rows�colsr+r#r#r$�from_pretrained�s












zEmbedding.from_pretrained)NNrFFNNN)TNNrFF)�__name__� __module__�__qualname__�__doc__� __constants__�intrrrr �floatrr�boolrrrrrrr&r,�strr0�classmethodr8� __classcell__r#r#)
r"r$r s. _











0


r c s
eZ
dZUd
Zdddddddd d g Zeeee  e e eeeeeed eeee e eeeeeeeedd��f
dd� Zdd�
dd�Zdd�
dd�Zd!eeeeeed�dd�Zed�
dd�Zed"eeee e eeeeeedd� dd��
Z�ZS)#�EmbeddingBagaComputes 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 (boolean, 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 (string, 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) >>> 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') rrrrr�moder�include_last_offsetr N�@F�mean)rrrrrrErrrFr rc s�||d
�} tt
|�j�
|
|_||_||_||_||_| dk r�| dkrZ| |jks�td�
�
n&| dkr�| |jksvtd�
�
|j| } | |_ |dkr�t tj|
|ff
| �
�
|_ |j�
n$t|j�
|
|gks�td�
�
t |�
|_ ||_||_| |_dS)N)rrr
z)padding_idx must be within num_embeddingsz?Shape of weight does not match num_embeddings and embedding_dim)rrDrrrrrrrr rrrrrrrrErrF)r rrrrrrErrrFr rrr!)
r"r#r$r9
s.




















zEmbeddingBag.__init__)
rc

Cstj
|j�

|j�
dS)
N)r r%rr&)
r r#r#r$rW
s

zEmbeddingBag.reset_parametersc

Cs4|jdk r0t
j��
|j|jjd
�

WdQRXdS)Nr
)r rr'rr()
r r#r#r$r&[
s


z(EmbeddingBag._fill_padding_idx_with_zero)r)�offsets�per_sample_weightsrcCs.tj
|
|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*Z embedding_bagrrrrrErrFr )r r)rIrJr#r#r$r,`
s 



zEmbeddingBag.forwardc
Csbd
}
|jdk r|
d7}
|j
dkr(|
d7}
|jdk r:|
d7}
|
d7}
|jdk rT|
d7}
|
jf|j�
S) Nz!{num_embeddings}, {embedding_dim}z, max_norm={max_norm}rz, norm_type={norm_type}Fz), scale_grad_by_freq={scale_grad_by_freq}z , mode={mode}z, padding_idx={padding_idx})rrrr r-r.)r r/r#r#r$r0�
s










zEmbeddingBag.extra_reprT) r4r5rrrrErrFr rc CsH|
j�d
kst
d�
�
|
j\} }|| ||
||||||| d� }||j_|S)aQCreates EmbeddingBag instance from given 2-dimensional FloatTensor. Args: embeddings (Tensor): FloatTensor containing weights for the EmbeddingBag. First dimension is being passed to EmbeddingBag as 'num_embeddings', second as 'embedding_dim'. freeze (boolean, optional): If ``True``, the tensor does not get updated in the learning process. Equivalent to ``embeddingbag.weight.requires_grad = False``. Default: ``True`` max_norm (float, optional): See module initialization documentation. Default: ``None`` norm_type (float, optional): See module initialization documentation. Default ``2``. scale_grad_by_freq (boolean, optional): See module initialization documentation. Default ``False``. mode (string, optional): See module initialization documentation. Default: ``"mean"`` sparse (bool, optional): See module initialization documentation. Default: ``False``. include_last_offset (bool, optional): See module initialization documentation. Default: ``False``. padding_idx (int, optional): See module initialization documentation. Default: ``None``. Examples:: >>> # 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]]) >>> embeddingbag(input) tensor([[ 2.5000, 3.7000, 4.6500]]) rz4Embeddings parameter is expected to be 2-dimensional) rrrrrrrErrFr )r1rrrr2) r3r4r5rrrrErrFr r6r7Zembeddingbagr#r#r$r8�
s 














zEmbeddingBag.from_pretrained) NrGFrHFNFNNN)NN)TNrGFrHFFN)r9r:r;r<r=r>rrrr?rrr@rrrrArErrFr rrr&r,r0rBr8rCr#r#)
r"r$rD�s6 L














4% 



rD)�typingrrrZtorch.nn.parameterr�moduler�rr*r r rDr#r#r#r$�
s



R