pyabsa.networks.sa_encoder¶

Classes¶

`BertSelfAttention`	Base class for all neural network modules.
`Encoder`	Base class for all neural network modules.
`SelfAttention`	Base class for all neural network modules.

Module Contents¶

class pyabsa.networks.sa_encoder.BertSelfAttention(config)¶

Bases: torch.nn.Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested 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) -> None:
        super().__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 also have their parameters converted when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:: training (bool) – Boolean represents whether this module is in training or evaluation mode.

num_attention_heads¶

attention_head_size¶

all_head_size¶

query¶

key¶

value¶

dropout¶

position_embedding_type¶

is_decoder¶

transpose_for_scores(x)¶

forward(hidden_states, attention_mask=None, head_mask=None, encoder_hidden_states=None, encoder_attention_mask=None, past_key_value=None, output_attentions=False)¶

class pyabsa.networks.sa_encoder.Encoder(bert_config, config, layer_num=1)¶

Bases: torch.nn.Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested 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) -> None:
        super().__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 also have their parameters converted when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:: training (bool) – Boolean represents whether this module is in training or evaluation mode.

bert_config¶

config¶

encoder¶

tanh¶

forward(x)¶

Encodes a sequence using self-attention mechanism.

Parameters:: x – Input tensor of size (batch_size, seq_len, hidden_size)
Returns:: Encoded tensor of the same size as the input tensor

class pyabsa.networks.sa_encoder.SelfAttention(bert_config, config)¶

Bases: torch.nn.Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested 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) -> None:
        super().__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 also have their parameters converted when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:: training (bool) – Boolean represents whether this module is in training or evaluation mode.

bert_config¶

config¶

SA¶

forward(inputs)¶

Computes the context-aware representation of each token in the sequence using self-attention mechanism.

Parameters:: inputs – Input tensor of size (batch_size, seq_len, hidden_size)
Returns:: Encoded tensor of the same size as the input tensor