pyabsa.tasks.AspectPolarityClassification.models.__lcf__.dlcf_dca_bert

Classes

PointwiseFeedForward	A two-feed-forward-layer module
DLCF_DCA_BERT	Base class for all neural network modules.

Functions

weight_distrubute_local(bert_local_out, depend_weight, ...)

Module Contents

pyabsa.tasks.AspectPolarityClassification.models.__lcf__.dlcf_dca_bert.weight_distrubute_local(bert_local_out, depend_weight, depended_weight, depend_vec, depended_vec, config)

class pyabsa.tasks.AspectPolarityClassification.models.__lcf__.dlcf_dca_bert.PointwiseFeedForward(d_hid, d_inner_hid=None, d_out=None, dropout=0)

Bases: torch.nn.Module

A two-feed-forward-layer module

w_1

w_2

dropout

relu

forward(x)

class pyabsa.tasks.AspectPolarityClassification.models.__lcf__.dlcf_dca_bert.DLCF_DCA_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', 'text_raw_bert_indices', 'dlcf_vec', 'depend_vec', 'depended_vec']

bert4global

bert4local

hidden

config

dropout

bert_SA_

mean_pooling_double

bert_pooler

dense

dca_sa

dca_pool

dca_lin

weight_calculate(sa, pool, lin, d_w, ded_w, depend_out, depended_out)

forward(inputs)