基于BILSTM及其他RNN序列模型的人名分类器

数据集Kaggle链接

NameNationalLanguage | Kaggle

数据集分布:

第一列为人名,第二列为国家标签

代码开源地址

Kaggle代码链接

https://www.kaggle.com/code/houjijin/name-nationality-classification

Gitee码云链接

人名国籍分类 Name Nation classification: using BILSTM to predict individual's nationality by their name

github链接

GitHub - Foxbabe1q/Name-Nation-classification: Use BILSTM to do the classification of individuals by their names

RNN序列模型类编写

import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F



device = torch.device('mps') if torch.backends.mps.is_available() else torch.device('cpu')

class SimpleRNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers):
        super(SimpleRNN, self).__init__()
        self.hidden_size = hidden_size
        self.input_size = input_size
        self.num_layers = num_layers
        self.output_size = 18
        self.rnn = nn.RNN(input_size, hidden_size, num_layers = num_layers, batch_first=True)
        self.fc = nn.Linear(self.hidden_size, self.output_size)

    def forward(self, x, hidden):
        output, hidden = self.rnn(x, hidden)
        output = output[:, -1, :]
        output = self.fc(output)
        return output, hidden

    def init_hidden(self, batch_size):
        hidden = torch.zeros(self.num_layers, batch_size, self.hidden_size, device=device)
        return hidden

class SimpleLSTM(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers):
        super(SimpleLSTM, self).__init__()
        self.hidden_size = hidden_size
        self.input_size = input_size
        self.num_layers = num_layers
        self.output_size = 18
        self.rnn = nn.LSTM(input_size, hidden_size, num_layers=num_layers, batch_first=True)
        self.fc = nn.Linear(self.hidden_size, self.output_size)

    def forward(self, x, hidden, c):
        output, (hidden, c) = self.rnn(x, (hidden,