pyabsa.tasks.AspectPolarityClassification.models.__classic__.cabasc

Module Contents

Classes

Cabasc

Base class for all neural network modules.

class pyabsa.tasks.AspectPolarityClassification.models.__classic__.cabasc.Cabasc(embedding_matrix, config, _type='c')

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 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().__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 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', 'left_with_aspect_indices', 'right_with_aspect_indices']

context_attention(x_l, x_r, memory, memory_len, aspect_len)

locationed_memory(memory, memory_len)

# differ from description in paper here, but may be better for i in range(memory.size(0)):

for idx in range(memory_len[i]):

aspect_start = left_len[i] - aspect_len[i] aspect_end = left_len[i] if idx < aspect_start: l = aspect_start.item() - idx elif idx <= aspect_end: l = 0 else: l = idx - aspect_end.item() memory[i][idx] *= (1-float(l)/int(memory_len[i]))

forward(inputs)