--- title: Attention Layers keywords: fastai sidebar: home_sidebar summary: "Implementation of Attention modules including Multihead attention etc.." description: "Implementation of Attention modules including Multihead attention etc.." nb_path: "nbs/layers/attention.ipynb" ---
{% raw %}
{% endraw %} {% raw %}
{% endraw %} {% raw %}

class TokenEmbedding[source]

TokenEmbedding(vocab_size, embed_size=512) :: Embedding

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 (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)
{% endraw %} {% raw %}
{% endraw %} {% raw %}

class PositionalEmbedding[source]

PositionalEmbedding(max_len, d_model) :: Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:to, etc.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

{% endraw %} {% raw %}
{% endraw %} {% raw %}

class GELU[source]

GELU() :: Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:to, etc.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

{% endraw %} {% raw %}
{% endraw %} {% raw %}

class PositionwiseFeedForward[source]

PositionwiseFeedForward(d_model, d_ff) :: Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:to, etc.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

{% endraw %} {% raw %}
{% endraw %} {% raw %}

class LayerNorm[source]

LayerNorm(features, eps=1e-06) :: Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:to, etc.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

{% endraw %} {% raw %}
{% endraw %} {% raw %}

class SublayerConnection[source]

SublayerConnection(size, dropout) :: Module

layer norm and dropout (dropout and then layer norm)

{% endraw %} {% raw %}
{% endraw %} {% raw %}

class Attention[source]

Attention() :: Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:to, etc.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

{% endraw %} {% raw %}
{% endraw %} {% raw %}

class MultiHeadedAttention[source]

MultiHeadedAttention(h, d_model, head_size=None, dropout=0.1) :: Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:to, etc.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

{% endraw %} {% raw %}
{% endraw %} {% raw %}

class TransformerBlock[source]

TransformerBlock(hidden, attn_heads, head_size, feed_forward_hidden, dropout, attn_dropout=0.1) :: Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:to, etc.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

{% endraw %} {% raw %}
{% endraw %} {% raw %}

class SASMultiHeadedAttention[source]

SASMultiHeadedAttention(h, d_model, head_size=None, dropout=0.1) :: Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:to, etc.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

{% endraw %} {% raw %}
{% endraw %} {% raw %}

class SASPositionwiseFeedForward[source]

SASPositionwiseFeedForward(d_model, d_ff, dropout=0.1) :: Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:to, etc.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

{% endraw %} {% raw %}
{% endraw %} {% raw %}

class SASTransformerBlock[source]

SASTransformerBlock(hidden, attn_heads, head_size, feed_forward_hidden, dropout, attn_dropout=0.1) :: Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:to, etc.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

{% endraw %} {% raw %}
{% endraw %}

References

  1. https://github.com/sparsh-ai/stanza/blob/S714864/model/attention.py