1、名字分类数据

????????数据准备：?

????????补零：

????????国家对照：

2、bi-directional双向循环神经网络

?????????反向传播计算一次。

3、pack_padded_sequence作用

????????堆叠未排序不可行：

????????先根据长度来排序：

?

4、代码实现名字分类

???代码如下：

import math
import matplotlib.pyplot as plt
import numpy as np
import torch
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
import gzip
import csv
import time


HIDDEN_SIZE = 100
BATCH_SIZE = 256
N_LAYER = 2
N_EPOCHS = 50
N_CHARS = 128  # 这个是为了构造嵌入层
USE_GPU = False  # 使用GPU会报错


class NameDataset(Dataset):
    def __init__(self, is_train_set):
        filename = './names_train.csv.gz' if is_train_set else './names_test.csv.gz'
        with gzip.open(filename, 'rt') as f:  # r表示只读，从文件头开始，t表示文本模式
            reader = csv.reader(f)
            rows = list(reader)  # 读出名字和语言
        self.names = [row[0] for row in rows]
        self.len = len(self.names)
        self.countries = [row[1] for row in rows]

        self.country_list = list(sorted(set(self.countries)))  # set变成集合，然后排序
        self.country_dict = self.getCountryDict()  # 变成词典
        self.country_num = len(self.country_list)

    def __getitem__(self, index):  # 根据索引拿到的是名字，国家的索引
        return self.names[index], self.country_dict[self.countries[index]]

    def __len__(self):
        return self.len

    def getCountryDict(self):
        country_dict = dict()
        for idx, country_name in enumerate(self.country_list, 0):
            country_dict[country_name] = idx
        return country_dict

    def idx2country(self, index):
        return self.country_list[index]  # 根据索引返回国家字符串

    def getCountriesNum(self):
        return self.country_num  # 返回国家数量



trainSet = NameDataset(is_train_set=True)
trainLoader = DataLoader(trainSet, batch_size=BATCH_SIZE, shuffle=True)
testSet = NameDataset(is_train_set=False)
testLoader = DataLoader(testSet, batch_size=BATCH_SIZE, shuffle=False)

N_COUNTRY = trainSet.getCountriesNum()


class RNNClassifier(torch.nn.Module):
    def __init__(self, input_size, hidden_size, output_size, n_layers=1, bidirectional=True):  # bidirectional单向还是双向
        super(RNNClassifier, self).__init__()
        self.hidden_size = hidden_size
        self.n_layers = n_layers
        self.n_directions = 2 if bidirectional else 1  # 双向2单向1

        # 嵌入层（𝑠𝑒𝑞𝐿𝑒𝑛, 𝑏𝑎𝑡𝑐?𝑆𝑖𝑧𝑒） --> (𝑠𝑒𝑞𝐿𝑒𝑛, 𝑏𝑎𝑡𝑐?𝑆𝑖𝑧𝑒, hidden_size)
        self.embedding = torch.nn.Embedding(input_size, hidden_size)
        self.gru = torch.nn.GRU(hidden_size, hidden_size, n_layers, bidirectional=bidirectional)
        self.fc = torch.nn.Linear(hidden_size * self.n_directions, output_size)
        # hidden_size * self.n_directions拼接在一起

    def _init_hidden(self, batch_size):
        hidden = torch.zeros(self.n_layers * self.n_directions, batch_size, self.hidden_size)
        return create_tensor(hidden)

    def forward(self, input, seq_lengths):
        # input shape : B x S -> S x B
        input = input.t()  # 转置
        batch_size = input.size(1)

        hidden = self._init_hidden(batch_size)
        embedding = self.embedding(input)

        # pack them up
        gru_input = torch.nn.utils.rnn.pack_padded_sequence(embedding, seq_lengths)
        # 提速

        output, hidden = self.gru(gru_input, hidden)
        if self.n_directions == 2:
            hidden_cat = torch.cat([hidden[-1], hidden[-2]], dim=1)  # 两个就拼起来
        else:
            hidden_cat = hidden[-1]
        fc_output = self.fc(hidden_cat)
        return fc_output


def create_tensor(tensor):
    if USE_GPU:
        device = torch.device("cuda:0")
        tensor = tensor.to(device)
    return tensor


def name2list(name):
    arr = [ord(c) for c in name]
    return arr, len(arr)


def make_tensors(names, countries):
    sequences_and_lengths = [name2list(name) for name in names]  # 每个名字变成列表
    name_sequences = [s1[0] for s1 in sequences_and_lengths]  # 拿出列表长度
    seq_lengths = torch.LongTensor([s1[1] for s1 in sequences_and_lengths])  # 序列长度转换
    countries = countries.long()  # 转换成long

    # make tensor of name, BatchSize * seqLen，padding操作
    seq_tensor = torch.zeros(len(name_sequences), seq_lengths.max()).long()
    # 补零的方式先将所有的0 Tensor给初始化出来，然后在每行前面填充每个名字
    for idx, (seq, seq_len) in enumerate(zip(name_sequences, seq_lengths), 0):
        seq_tensor[idx, :seq_len] = torch.LongTensor(seq)

    # sort by length to use pack_padded_sequence
    # 将名字长度降序排列，并且返回降序之后的长度在原tensor中的小标perm_idx
    seq_lengths, perm_idx = seq_lengths.sort(dim=0, descending=True)
    seq_tensor = seq_tensor[perm_idx]
    countries = countries[perm_idx]

    # 返回排序之后名字Tensor，排序之后的名字长度Tensor，排序之后的国家名字Tensor
    return create_tensor(seq_tensor),\
           create_tensor(seq_lengths), \
           create_tensor(countries)


# 模型训练
def trainModel():
    total_loss = 0
    for i, (names, countries) in enumerate(trainLoader, 1):
        inputs, seq_lengths, target = make_tensors(names, countries)
        output = classifier(inputs, seq_lengths)
        loss = criterion(output, target)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        total_loss += loss.item()

        print(f'[{time_since(start)}] Epoch {epoch}', end=' ')
        print(f'[{i * len(inputs)}/{len(trainSet)}]', end=' ')
        print(f'loss = {total_loss / (i * len(inputs))}')
        return total_loss


# 模型测试
def testModel():
    correct = 0
    total = len(testSet)
    print("evaluating train model .....")
    with torch.no_grad():
        for i, (names, countries) in enumerate(testLoader, 1):
            inputs, seq_lengths, target = make_tensors(names, countries)
            output = classifier(inputs, seq_lengths)
            pred = output.max(dim=1, keepdim=True)[1]
            correct += pred.eq(target.view_as(pred)).sum().item()

        percent = '%.2f' % (100 * correct / total)
        print(f'Test set: Accuracy {correct} / {total} {percent}%', '\n')

    return correct / total


def time_since(since):
    s = time.time() - since
    m = math.floor(s / 60)
    s -= m * 60
    return '%dm %ds' % (m, s)


# 主过程
if __name__ == '__main__':
    classifier = RNNClassifier(N_CHARS, HIDDEN_SIZE, N_COUNTRY, N_LAYER)
    # N_CHARS字母表的数量，
    if USE_GPU:
        device = torch.device("cuda:0")
        classifier.to(device)

    criterion = torch.nn.CrossEntropyLoss()
    optimizer = torch.optim.Adam(classifier.parameters(), lr=0.001)

    start = time.time()  # 计算时间
    print("Training for %d epochs..." % N_EPOCHS)
    acc_list = []
    for epoch in range(1, N_EPOCHS + 1):
        trainModel()
        acc = testModel()
        acc_list.append(acc)

    epoch = np.arange(1, len(acc_list) + 1)
    acc_list = np.array(acc_list)
    plt.plot(epoch, acc_list)
    plt.xlabel('Epoch')
    plt.ylabel('Accuracy')
    plt.grid()
    plt.show()

?????????使用GPU会报错，暂未解决这个问题。

????????结果如下：