pyabsa.tasks.AspectPolarityClassification.models.__plm__.tnet_lf_bert

Classes

Absolute_Position_Embedding	Base class for all neural network modules.
TNet_LF_BERT_Unit	Base class for all neural network modules.
TNet_LF_BERT	Base class for all neural network modules.

Module Contents

class pyabsa.tasks.AspectPolarityClassification.models.__plm__.tnet_lf_bert.Absolute_Position_Embedding(config, size=None, mode='sum')

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.

config

size = None

mode = 'sum'

forward(x, pos_inx)

weight_matrix(pos_inx, batch_size, seq_len)

class pyabsa.tasks.AspectPolarityClassification.models.__plm__.tnet_lf_bert.TNet_LF_BERT_Unit(bert, 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.

embed

position

config

lstm1

lstm2

convs3

fc1

fc

forward(inputs)

class pyabsa.tasks.AspectPolarityClassification.models.__plm__.tnet_lf_bert.TNet_LF_BERT(bert, 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.

inputs = ['text_indices', 'aspect_indices', 'aspect_boundary', 'left_aspect_indices',...

config

asgcn_left

asgcn_central

asgcn_right

dropout

pooler

linear

dense

forward(inputs)