pyabsa.tasks.AspectSentimentTripletExtraction.models.model¶

Classes¶

`LayerNorm`	Construct a layernorm module (See citation for details).
`RefiningStrategy`	Base class for all neural network modules.
`GraphConvLayer`	A GCN module operated on dependency graphs.
`Biaffine`	Base class for all neural network modules.
`EMCGCN`	Base class for all neural network modules.

Module Contents¶

class pyabsa.tasks.AspectSentimentTripletExtraction.models.model.LayerNorm(features, eps=1e-06)¶

Bases: torch.nn.Module

Construct a layernorm module (See citation for details).

a_2¶

b_2¶

eps = 1e-06¶

forward(x)¶

class pyabsa.tasks.AspectSentimentTripletExtraction.models.model.RefiningStrategy(hidden_dim, edge_dim, dim_e, dropout_ratio=0.5)¶

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.

hidden_dim¶

edge_dim¶

dim_e¶

dropout = 0.5¶

W¶

forward(edge, node1, node2)¶

class pyabsa.tasks.AspectSentimentTripletExtraction.models.model.GraphConvLayer(device, gcn_dim, edge_dim, dep_embed_dim, pooling='avg')¶

Bases: torch.nn.Module

A GCN module operated on dependency graphs.

gcn_dim¶

edge_dim¶

dep_embed_dim¶

device¶

pooling = 'avg'¶

layernorm¶

W¶

highway¶

forward(weight_prob_softmax, weight_adj, gcn_inputs, self_loop)¶

class pyabsa.tasks.AspectSentimentTripletExtraction.models.model.Biaffine(config, in1_features, in2_features, out_features, bias=(True, True))¶

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¶

in1_features¶

in2_features¶

out_features¶

bias = (True, True)¶

linear_input_size¶

linear_output_size¶

linear¶

forward(input1, input2)¶

class pyabsa.tasks.AspectSentimentTripletExtraction.models.model.EMCGCN(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 = ['tokens', 'masks', 'word_pair_position', 'word_pair_deprel', 'word_pair_pos', 'word_pair_synpost']¶

config¶

dropout_output¶

post_emb¶

deprel_emb¶

postag_emb¶

synpost_emb¶

triplet_biaffine¶

ap_fc¶

op_fc¶

dense¶

num_layers¶

gcn_layers¶

layernorm¶

forward(inputs)¶