NLP实验——基于MLP的姓氏分类任务

NLP实验——基于MLP的姓氏分类任务

 

实验介绍

实验内容

在这一实验中，我们将探索传统上称为前馈网络的神经网络模型，以及一种前馈神经网络：多层感知器。多层感知器在结构上扩展了简单感知机，把多个感知机分组在一个单层，并将多个层叠加在一起。我们稍后将介绍多层感知器，并在使用带有多层感知器的姓氏分类中展示它们在多层分类中的应用。

在我们介绍这些不同的模型时，需要理解事物如何工作的一个有用方法是在计算数据张量时注意它们的大小和形状。每种类型的神经网络层对它所计算的数据张量的大小和形状都有特定的影响，理解这种影响可以极大地有助于对这些模型的深入理解。

实验要点

• 通过完成使用“带有多层感知器的姓氏分类”实验掌握多层感知器在多层分类中的应用
• 掌握每种类型的神经网络层对它所计算的数据张量的大小和形状的影响

实验环境

• Python 3.6.7
• PyTorch 1.0.0
• 希冀平台
• Jupyter Notebook

基本网络介绍

多层感知器（MLP）

多层感知器（MLP, Multi-Layer Perceptron）是一种常见的前馈神经网络，通常用于分类和回归任务。

MLP的基本结构

MLP由一个输入层、一个或多个隐藏层和一个输出层组成。每一层由若干神经元（或节点）构成，神经元之间通过权重连接，如图所示：

工作原理

MLP的工作原理可以分为以下几个步骤：

1. 前向传播：

   • 输入数据通过输入层传递到隐藏层。在隐藏层，每个神经元对接收到的输入进行加权求和，并通过激活函数计算输出。
   • 隐藏层的输出传递到输出层，输出层根据任务需要计算最终结果。

2. 损失计算：

   • 计算模型的预测结果与真实结果之间的误差，通常使用损失函数进行度量。常见的损失函数有：
     • 交叉熵（CrossEntropy）损失，一般用于分类任务：
       $$\mathcal{L}=-\frac{1}{N}\sum _{i=1}^N\sum _{j=1}^C{y}_{ij}\log (\widehat{y_{ij}})$$
     • 均方误差（MSE），一般用于回归任务：
       $$\mathcal{L}=\frac{1}{N}\sum _{i=1}^N(y_i-\widehat{y_i}{)}^2$$
       假设$y_i$是实际标签的one-hot向量，$\widehat{y_i}$是模型的预测概率向量，$N$是样本总数，$C$是类别数。

3. 反向传播：

   • 通过链式法则计算损失函数对各层权重的梯度。然后通过梯度下降算法或其变体（如Adam优化器）更新权重。

4. 迭代训练：

   • 以上过程在训练数据上反复进行，直到模型的性能达到预期要求或训练次数达到预设值。

MLP的优势

1. 灵活性：MLP能够处理各种复杂的非线性关系。
2. 通用性：MLP适用于分类、回归等多种任务。

实验步骤

导入相关库

本实验使用PyTorch架构。

from argparse import Namespace
from collections import Counter
import json
import os
import string

import numpy as np
import pandas as pd
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.utils.data import Dataset, DataLoader
from tqdm import tqdm_notebook

数据集介绍

姓氏数据集（SurnameDataset），它收集了来自18个不同国家的10,000个姓氏，这些姓氏是作者从互联网上不同的姓名来源收集的。
数据集部分数据截图如下：

 

性质

• 该数据集是相当不平衡的。排名前三的类别占数据的60%以上:27%是英语，21%是俄语，14%是阿拉伯语。剩下的15个民族的频率也在下降——这也是语言特有的特性。
• 在国籍和姓氏正字法(拼写)之间有一种有效和直观的关系。有些拼写变体与原籍国联系非常紧密(比如“O ‘Neill”、“Antonopoulos”、“Nagasawa”或“Zhu”)。

数据预处理

为了创建最终的数据集，我们从一个比课程补充材料中包含的版本处理更少的版本开始，并执行了几个数据集修改操作。第一个目的是减少这种不平衡——原始数据集中70%以上是俄文，这可能是由于抽样偏差或俄文姓氏的增多。为此，我们通过选择标记为俄语的姓氏的随机子集对这个过度代表的类进行子样本。接下来，我们根据国籍对数据集进行分组，并将数据集分为三个部分:70%到训练数据集，15%到验证数据集，最后15%到测试数据集，以便跨这些部分的类标签分布具有可比性。

生成surnames_with_splits.csv文件

import collections
import numpy as np
import pandas as pd
import re

from argparse import Namespace

args = Namespace(
    raw_dataset_csv="data/surnames/surnames.csv",
    train_proportion=0.7,
    val_proportion=0.15,
    test_proportion=0.15,
    output_munged_csv="data/surnames/surnames_with_splits.csv",
    seed=1337
)

# Read raw data
surnames = pd.read_csv(args.raw_dataset_csv, header=0)

surnames.head()

# Unique classes
set(surnames.nationality)

# Splitting train by nationality
# Create dict
by_nationality = collections.defaultdict(list)
for _, row in surnames.iterrows():
    by_nationality[row.nationality].append(row.to_dict())

# Create split data
final_list = []
np.random.seed(args.seed)
for _, item_list in sorted(by_nationality.items()):
    np.random.shuffle(item_list)
    n = len(item_list)
    n_train = int(args.train_proportion*n)
    n_val = int(args.val_proportion*n)
    n_test = int(args.test_proportion*n)
    
    # Give data point a split attribute
    for item in item_list[:n_train]:
        item['split'] = 'train'
    for item in item_list[n_train:n_train+n_val]:
        item['split'] = 'val'
    for item in item_list[n_train+n_val:]:
        item['split'] = 'test'  
    
    # Add to final list
    final_list.extend(item_list)

# Write split data to file
final_surnames = pd.DataFrame(final_list)

final_surnames.split.value_counts()

final_surnames.head()

# Write munged data to CSV
final_surnames.to_csv(args.output_munged_csv, index=False)

SurnameDataset类以及相关函数的建立

话不多说，直接上代码：

class SurnameDataset(Dataset):
    def __init__(self, surname_df, vectorizer):
        """
        Args:
            surname_df (pandas.DataFrame): the dataset
            vectorizer (SurnameVectorizer): vectorizer instatiated from dataset
        """
        self.surname_df = surname_df
        self._vectorizer = vectorizer

        self.train_df = self.surname_df[self.surname_df.split=='train']
        self.train_size = len(self.train_df)

        self.val_df = self.surname_df[self.surname_df.split=='val']
        self.validation_size = len(self.val_df)

        self.test_df = self.surname_df[self.surname_df.split=='test']
        self.test_size = len(self.test_df)

        self._lookup_dict = {'train': (self.train_df, self.train_size),
                             'val': (self.val_df, self.validation_size),
                             'test': (self.test_df, self.test_size)}

        self.set_split('train')
        
        # Class weights
        class_counts = surname_df.nationality.value_counts().to_dict()
        def sort_key(item):
            return self._vectorizer.nationality_vocab.lookup_token(item[0])
        sorted_counts = sorted(class_counts.items(), key=sort_key)
        frequencies = [count for _, count in sorted_counts]
        self.class_weights = 1.0 / torch.tensor(frequencies, dtype=torch.float32)

    @classmethod
    def load_dataset_and_make_vectorizer(cls, surname_csv):
        """Load dataset and make a new vectorizer from scratch
        
        Args:
            surname_csv (str): location of the dataset
        Returns:
            an instance of SurnameDataset
        """
        surname_df = pd.read_csv(surname_csv)
        train_surname_df = surname_df[surname_df.split=='train']
        return cls(surname_df, SurnameVectorizer.from_dataframe(train_surname_df))

    @classmethod
    def load_dataset_and_load_vectorizer(cls, surname_csv, vectorizer_filepath):
        """Load dataset and the corresponding vectorizer. 
        Used in the case in the vectorizer has been cached for re-use
        
        Args:
            surname_csv (str): location of the dataset
            vectorizer_filepath (str): location of the saved vectorizer
        Returns:
            an instance of SurnameDataset
        """
        surname_df = pd.read_csv(surname_csv)
        vectorizer = cls.load_vectorizer_only(vectorizer_filepath)
        return cls(surname_df, vectorizer)

    @staticmethod
    def load_vectorizer_only(vectorizer_filepath):
        """a static method for loading the vectorizer from file
        
        Args:
            vectorizer_filepath (str): the location of the serialized vectorizer
        Returns:
            an instance of SurnameVectorizer
        """
        with open(vectorizer_filepath) as fp:
            return SurnameVectorizer.from_serializable(json.load(fp))

    def save_vectorizer(self, vectorizer_filepath):
        """saves the vectorizer to disk using json
        
        Args:
            vectorizer_filepath (str): the location to save the vectorizer
        """
        with open(vectorizer_filepath, "w") as fp:
            json.dump(self._vectorizer.to_serializable(), fp)

    def get_vectorizer(self):
        """ returns the vectorizer """
        return self._vectorizer

    def set_split(self, split="train"):
        """ selects the splits in the dataset using a column in the dataframe """
        self._target_split = split
        self._target_df, self._target_size = self._lookup_dict[split]

    def __len__(self):
        return self._target_size

    def __getitem__(self, index):
        """the primary entry point method for PyTorch datasets
        
        Args:
            index (int): the index to the data point 
        Returns:
            a dictionary holding the data point's:
                features (x_surname)
                label (y_nationality)
        """
        row = self._target_df.iloc[index]

        surname_vector = \
            self._vectorizer.vectorize(row.surname)

        nationality_index = \
            self._vectorizer.nationality_vocab.lookup_token(row.nationality)

        return {'x_surname': surname_vector,
                'y_nationality': nationality_index}

    def get_num_batches(self, batch_size):
        """Given a batch size, return the number of batches in the dataset
        
        Args:
            batch_size (int)
        Returns:
            number of batches in the dataset
        """
        return len(self) // batch_size

    
def generate_batches(dataset, batch_size, shuffle=True,
                     drop_last=True, device="cpu"): 
    """
    A generator function which wraps the PyTorch DataLoader. It will 
      ensure each tensor is on the write device location.
    """
    dataloader = DataLoader(dataset=dataset, batch_size=batch_size,
                            shuffle=shuffle, drop_last=drop_last)

    for data_dict in dataloader:
        out_data_dict = {}
        for name, tensor in data_dict.items():
            out_data_dict[name] = data_dict[name].to(device)
        yield out_data_dict

词汇表、向量化器、分类器

为了使用字符对姓氏进行分类，我们使用词汇表（Vocabulary）、向量化器（SurnameVectorizer）和数据加载器（DataLoader）将姓氏字符串转换为向量化的minibatches。
数据不是通过将字令牌（token）映射到整数来向量化的，而是通过将字符映射到整数来向量化的。换句话说，本实验中的token是字母，而不是单词。

词汇表（Vocabulary）

简要概述一下，词汇表是两个Python字典的协调，这两个字典在令牌(在本例中是字符)和整数之间形成一个双射；也就是说，第一个字典将字符映射到整数索引，第二个字典将整数索引映射到字符。add_token方法用于向词汇表中添加新的令牌，lookup_token方法用于检索索引，lookup_index方法用于检索给定索引的令牌(在推断阶段很有用)。我们在本实验中使用的是one-hot词汇表，不计算字符出现的频率，只对频繁出现的条目进行限制。这主要是因为数据集很小，而且大多数字符足够频繁。

class Vocabulary(object):
    """Class to process text and extract vocabulary for mapping"""

    def __init__(self, token_to_idx=None, add_unk=True, unk_token="<UNK>"):
        """
        Args:
            token_to_idx (dict): a pre-existing map of tokens to indices
            add_unk (bool): a flag that indicates whether to add the UNK token
            unk_token (str): the UNK token to add into the Vocabulary
        """

        if token_to_idx is None:
            token_to_idx = {}
        self._token_to_idx = token_to_idx

        self._idx_to_token = {idx: token 
                              for token, idx in self._token_to_idx.items()}
        
        self._add_unk = add_unk
        self._unk_token = unk_token
        
        self.unk_index = -1
        if add_unk:
            self.unk_index = self.add_token(unk_token) 
        
        
    def to_serializable(self):
        """ returns a dictionary that can be serialized """
        return {'token_to_idx': self._token_to_idx, 
                'add_unk': self._add_unk, 
                'unk_token': self._unk_token}

    @classmethod
    def from_serializable(cls, contents):
        """ instantiates the Vocabulary from a serialized dictionary """
        return cls(**contents)

    def add_token(self, token):
        """Update mapping dicts based on the token.

        Args:
            token (str): the item to add into the Vocabulary
        Returns:
            index (int): the integer corresponding to the token
        """
        try:
            index = self._token_to_idx[token]
        except KeyError:
            index = len(self._token_to_idx)
            self._token_to_idx[token] = index
            self._idx_to_token[index] = token
        return index
    
    def add_many(self, tokens):
        """Add a list of tokens into the Vocabulary
        
        Args:
            tokens (list): a list of string tokens
        Returns:
            indices (list): a list of indices corresponding to the tokens
        """
        return [self.add_token(token) for token in tokens]

    def lookup_token(self, token):
        """Retrieve the index associated with the token 
          or the UNK index if token isn't present.
        
        Args:
            token (str): the token to look up 
        Returns:
            index (int): the index corresponding to the token
        Notes:
            `unk_index` needs to be >=0 (having been added into the Vocabulary) 
              for the UNK functionality 
        """
        if self.unk_index >= 0:
            return self._token_to_idx.get(token, self.unk_index)
        else:
            return self._token_to_idx[token]

    def lookup_index(self, index):
        """Return the token associated with the index
        
        Args: 
            index (int): the index to look up
        Returns:
            token (str): the token corresponding to the index
        Raises:
            KeyError: if the index is not in the Vocabulary
        """
        if index not in self._idx_to_token:
            raise KeyError("the index (%d) is not in the Vocabulary" % index)
        return self._idx_to_token[index]

    def __str__(self):
        return "<Vocabulary(size=%d)>" % len(self)

    def __len__(self):
        return len(self._token_to_idx)

向量化器（SurnameVectorizer）

虽然词汇表将单个令牌(字符)转换为整数，但SurnameVectorizer负责应用词汇表并将姓氏转换为向量。在本次实验中，字符串没有在空格上分割。姓氏是字符的序列，每个字符在我们的词汇表中是一个单独的标记。然而，在CNN出现之前，我们将忽略序列信息，通过迭代字符串输入中的每个字符来创建输入的收缩one-hot向量表示。我们为以前未遇到的字符指定一个特殊的令牌，即UNK。由于我们仅从训练数据实例化词汇表，而且验证或测试数据中可能有惟一的字符，所以在字符词汇表中仍然使用UNK符号。

class SurnameVectorizer(object):
    """ The Vectorizer which coordinates the Vocabularies and puts them to use"""
    def __init__(self, surname_vocab, nationality_vocab):
        """
        Args:
            surname_vocab (Vocabulary): maps characters to integers
            nationality_vocab (Vocabulary): maps nationalities to integers
        """
        self.surname_vocab = surname_vocab
        self.nationality_vocab = nationality_vocab

    def vectorize(self, surname):
        """
        Args:
            surname (str): the surname

        Returns:
            one_hot (np.ndarray): a collapsed one-hot encoding 
        """
        vocab = self.surname_vocab
        one_hot = np.zeros(len(vocab), dtype=np.float32)
        for token in surname:
            one_hot[vocab.lookup_token(token)] = 1

        return one_hot

    @classmethod
    def from_dataframe(cls, surname_df):
        """Instantiate the vectorizer from the dataset dataframe
        
        Args:
            surname_df (pandas.DataFrame): the surnames dataset
        Returns:
            an instance of the SurnameVectorizer
        """
        surname_vocab = Vocabulary(unk_token="@")
        nationality_vocab = Vocabulary(add_unk=False)

        for index, row in surname_df.iterrows():
            for letter in row.surname:
                surname_vocab.add_token(letter)
            nationality_vocab.add_token(row.nationality)

        return cls(surname_vocab, nationality_vocab)

    @classmethod
    def from_serializable(cls, contents):
        surname_vocab = Vocabulary.from_serializable(contents['surname_vocab'])
        nationality_vocab =  Vocabulary.from_serializable(contents['nationality_vocab'])
        return cls(surname_vocab=surname_vocab, nationality_vocab=nationality_vocab)

    def to_serializable(self):
        return {'surname_vocab': self.surname_vocab.to_serializable(),
                'nationality_vocab': self.nationality_vocab.to_serializable()}

分类器（SurnameClassifier）

SurnameClassifier是本实验前面介绍的MLP。第一个线性层将输入向量映射到中间向量，并对该向量应用非线性。第二线性层将中间向量映射到预测向量。

在最后一步中，可选地应用softmax操作，以确保输出和为1;这就是所谓的“概率”。它是可选的原因与我们使用的损失函数的数学公式有关——交叉熵损失。我们研究了“损失函数”中的交叉熵损失。回想一下，交叉熵损失对于多类分类是最理想的，但是在训练过程中软最大值的计算不仅浪费而且在很多情况下并不稳定。

class SurnameClassifier(nn.Module):
    """ A 2-layer Multilayer Perceptron for classifying surnames """
    def __init__(self, input_dim, hidden_dim, output_dim):
        """
        Args:
            input_dim (int): the size of the input vectors
            hidden_dim (int): the output size of the first Linear layer
            output_dim (int): the output size of the second Linear layer
        """
        super(SurnameClassifier, self).__init__()
        self.fc1 = nn.Linear(input_dim, hidden_dim)
        self.fc2 = nn.Linear(hidden_dim, output_dim)

    def forward(self, x_in, apply_softmax=False):
        """The forward pass of the classifier
        
        Args:
            x_in (torch.Tensor): an input data tensor. 
                x_in.shape should be (batch, input_dim)
            apply_softmax (bool): a flag for the softmax activation
                should be false if used with the Cross Entropy losses
        Returns:
            the resulting tensor. tensor.shape should be (batch, output_dim)
        """
        intermediate_vector = F.relu(self.fc1(x_in))
        prediction_vector = self.fc2(intermediate_vector)

        if apply_softmax:
            prediction_vector = F.softmax(prediction_vector, dim=1)

        return prediction_vector

训练和测试

def make_train_state(args):
    return {'stop_early': False,
            'early_stopping_step': 0,
            'early_stopping_best_val': 1e8,
            'learning_rate': args.learning_rate,
            'epoch_index': 0,
            'train_loss': [],
            'train_acc': [],
            'val_loss': [],
            'val_acc': [],
            'test_loss': -1,
            'test_acc': -1,
            'model_filename': args.model_state_file}

def update_train_state(args, model, train_state):
    """Handle the training state updates.

    Components:
     - Early Stopping: Prevent overfitting.
     - Model Checkpoint: Model is saved if the model is better

    :param args: main arguments
    :param model: model to train
    :param train_state: a dictionary representing the training state values
    :returns:
        a new train_state
    """

    # Save one model at least
    if train_state['epoch_index'] == 0:
        torch.save(model.state_dict(), train_state['model_filename'])
        train_state['stop_early'] = False

    # Save model if performance improved
    elif train_state['epoch_index'] >= 1:
        loss_tm1, loss_t = train_state['val_loss'][-2:]

        # If loss worsened
        if loss_t >= train_state['early_stopping_best_val']:
            # Update step
            train_state['early_stopping_step'] += 1
        # Loss decreased
        else:
            # Save the best model
            if loss_t < train_state['early_stopping_best_val']:
                torch.save(model.state_dict(), train_state['model_filename'])

            # Reset early stopping step
            train_state['early_stopping_step'] = 0

        # Stop early ?
        train_state['stop_early'] = \
            train_state['early_stopping_step'] >= args.early_stopping_criteria

    return train_state

# compute accuracy
def compute_accuracy(y_pred, y_target):
    _, y_pred_indices = y_pred.max(dim=1)
    n_correct = torch.eq(y_pred_indices, y_target).sum().item()
    return n_correct / len(y_pred_indices) * 100

# set random seed
def set_seed_everywhere(seed, cuda):
    np.random.seed(seed)
    torch.manual_seed(seed)
    if cuda:
        torch.cuda.manual_seed_all(seed)

# handle directories
def handle_dirs(dirpath):
    if not os.path.exists(dirpath):
        os.makedirs(dirpath)

args = Namespace(
    # Data and path information
    surname_csv="data/surnames/surnames_with_splits.csv",
    vectorizer_file="vectorizer.json",
    model_state_file="model.pth",
    save_dir="model_storage/ch4/surname_mlp",
    # Model hyper parameters
    hidden_dim=300,
    # Training  hyper parameters
    seed=1337,
    num_epochs=100,
    early_stopping_criteria=5,
    learning_rate=0.001,
    batch_size=64,
    # Runtime options omitted for space
    # Runtime options
    cuda=False,
    reload_from_files=False,
    expand_filepaths_to_save_dir=True
)

if args.expand_filepaths_to_save_dir:
    args.vectorizer_file = os.path.join(args.save_dir,
                                        args.vectorizer_file)

    args.model_state_file = os.path.join(args.save_dir,
                                         args.model_state_file)
    
    print("Expanded filepaths: ")
    print("\t{}".format(args.vectorizer_file))
    print("\t{}".format(args.model_state_file))
    
# Check CUDA
if not torch.cuda.is_available():
    args.cuda = False

args.device = torch.device("cuda" if args.cuda else "cpu")
    
print("Using CUDA: {}".format(args.cuda))


# Set seed for reproducibility
set_seed_everywhere(args.seed, args.cuda)

# handle dirs
handle_dirs(args.save_dir)

训练中最显著的差异与模型中输出的种类和使用的损失函数有关。在这个例子中，输出是一个多类预测向量，可以转换为概率。正如在模型描述中所描述的，这种输出的损失类型仅限于CrossEntropyLoss和NLLLoss。由于它的简化，我们使用了CrossEntropyLoss。

dataset = SurnameDataset.load_dataset_and_make_vectorizer(args.surname_csv)
vectorizer = dataset.get_vectorizer()

classifier = SurnameClassifier(input_dim=len(vectorizer.surname_vocab),
                               hidden_dim=args.hidden_dim,
                               output_dim=len(vectorizer.nationality_vocab))

classifier = classifier.to(args.device)    

loss_func = nn.CrossEntropyLoss(dataset.class_weights)
optimizer = optim.Adam(classifier.parameters(), lr=args.learning_rate)

if args.reload_from_files:
    # training from a checkpoint
    print("Reloading!")
    dataset = SurnameDataset.load_dataset_and_load_vectorizer(argssurname_csv, args.vectorizer_file)
else:
    # create dataset and vectorizer
    print("Creating fresh!")
    dataset = SurnameDataset.load_dataset_and_make_vectorizer(args.surname_csv)
    dataset.save_vectorizer(args.vectorizer_file)
    
vectorizer = dataset.get_vectorizer()
classifier = SurnameClassifier(input_dim=len(vectorizer.surname_vocab), 
                               hidden_dim=args.hidden_dim, 
                               output_dim=len(vectorizer.nationality_vocab))
print(len(vectorizer.surname_vocab))

classifier = classifier.to(args.device)
dataset.class_weights = dataset.class_weights.to(args.device)

    
loss_func = nn.CrossEntropyLoss(dataset.class_weights)
optimizer = optim.Adam(classifier.parameters(), lr=args.learning_rate)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer=optimizer,
                                                 mode='min', factor=0.5,
                                                 patience=1)

train_state = make_train_state(args)

epoch_bar = tqdm_notebook(desc='training routine', 
                          total=args.num_epochs,
                          position=0)

dataset.set_split('train')
train_bar = tqdm_notebook(desc='split=train',
                          total=dataset.get_num_batches(args.batch_size), 
                          position=1, 
                          leave=True)
dataset.set_split('val')
val_bar = tqdm_notebook(desc='split=val',
                        total=dataset.get_num_batches(args.batch_size), 
                        position=1, 
                        leave=True)

try:
    for epoch_index in range(args.num_epochs):
        train_state['epoch_index'] = epoch_index

        # Iterate over training dataset

        # setup: batch generator, set loss and acc to 0, set train mode on

        dataset.set_split('train')
        batch_generator = generate_batches(dataset, 
                                           batch_size=args.batch_size, 
                                           device=args.device)
        running_loss = 0.0
        running_acc = 0.0
        classifier.train()

        for batch_index, batch_dict in enumerate(batch_generator):
            # the training routine is these 5 steps:

            # --------------------------------------
            # step 1. zero the gradients
            optimizer.zero_grad()

            # step 2. compute the output
            y_pred = classifier(batch_dict['x_surname'])

            # step 3. compute the loss
            loss = loss_func(y_pred, batch_dict['y_nationality'])
            loss_t = loss.item()
            running_loss += (loss_t - running_loss) / (batch_index + 1)

            # step 4. use loss to produce gradients
            loss.backward()

            # step 5. use optimizer to take gradient step
            optimizer.step()
            # -----------------------------------------
            # compute the accuracy
            acc_t = compute_accuracy(y_pred, batch_dict['y_nationality'])
            running_acc += (acc_t - running_acc) / (batch_index + 1)

            # update bar
            train_bar.set_postfix(loss=running_loss, acc=running_acc, 
                            epoch=epoch_index)
            train_bar.update()

        train_state['train_loss'].append(running_loss)
        train_state['train_acc'].append(running_acc)

        # Iterate over val dataset

        # setup: batch generator, set loss and acc to 0; set eval mode on
        dataset.set_split('val')
        batch_generator = generate_batches(dataset, 
                                           batch_size=args.batch_size, 
                                           device=args.device)
        running_loss = 0.
        running_acc = 0.
        classifier.eval()

        for batch_index, batch_dict in enumerate(batch_generator):

            # compute the output
            y_pred =  classifier(batch_dict['x_surname'])

            # step 3. compute the loss
            loss = loss_func(y_pred, batch_dict['y_nationality'])
            loss_t = loss.to("cpu").item()
            running_loss += (loss_t - running_loss) / (batch_index + 1)

            # compute the accuracy
            acc_t = compute_accuracy(y_pred, batch_dict['y_nationality'])
            running_acc += (acc_t - running_acc) / (batch_index + 1)
            val_bar.set_postfix(loss=running_loss, acc=running_acc, 
                            epoch=epoch_index)
            val_bar.update()

        train_state['val_loss'].append(running_loss)
        train_state['val_acc'].append(running_acc)

        train_state = update_train_state(args=args, model=classifier,
                                         train_state=train_state)

        scheduler.step(train_state['val_loss'][-1])

        if train_state['stop_early']:
            break

        train_bar.n = 0
        val_bar.n = 0
        epoch_bar.update()
except KeyboardInterrupt:
    print("Exiting loop")

# compute the loss & accuracy on the test set using the best available model

classifier.load_state_dict(torch.load(train_state['model_filename']))

classifier = classifier.to(args.device)
dataset.class_weights = dataset.class_weights.to(args.device)
loss_func = nn.CrossEntropyLoss(dataset.class_weights)

dataset.set_split('test')
batch_generator = generate_batches(dataset, 
                                   batch_size=args.batch_size, 
                                   device=args.device)
running_loss = 0.
running_acc = 0.
classifier.eval()

for batch_index, batch_dict in enumerate(batch_generator):
    # compute the output
    y_pred =  classifier(batch_dict['x_surname'])
    
    # compute the loss
    loss = loss_func(y_pred, batch_dict['y_nationality'])
    loss_t = loss.item()
    running_loss += (loss_t - running_loss) / (batch_index + 1)

    # compute the accuracy
    acc_t = compute_accuracy(y_pred, batch_dict['y_nationality'])
    running_acc += (acc_t - running_acc) / (batch_index + 1)

train_state['test_loss'] = running_loss
train_state['test_acc'] = running_acc

print("Test loss: {};".format(train_state['test_loss']))
print("Test Accuracy: {}%".format(train_state['test_acc']))

训练结束，测试结果如下：

模型评估

评价SurnameClassifier测试数据,我们将数据集设置为遍历测试数据,调用classifier.eval()方法,并遍历测试数据以同样的方式与其他数据。在这个例子中，调用classifier.eval()可以防止PyTorch在使用测试/评估数据时更新模型参数。

该模型对测试数据的准确性达到50%左右。如果在附带的notebook中运行训练例程，会注意到在训练数据上的性能更高。这是因为模型总是更适合它所训练的数据，所以训练数据的性能并不代表新数据的性能。如果遵循代码，你可以尝试隐藏维度的不同大小，应该注意到性能的提高。然而，这种增长不会很大，其主要原因是收缩的onehot向量化方法是一种弱表示。虽然它确实简洁地将每个姓氏表示为单个向量，但它丢弃了字符之间的顺序信息，这对于识别起源非常重要。

下面的示例显示了分类新姓氏的代码。给定一个姓氏作为字符串，该函数将首先应用向量化过程，然后获得模型预测。注意，我们包含了apply_softmax标志，所以结果包含概率。模型预测，在多项式的情况下，是类概率的列表。我们可以使用PyTorch张量最大函数来得到由最高预测概率表示的最优类。但是，我们不仅要看最好的预测，还要看更多的预测。例如，NLP中的标准实践是采用k-best预测并使用另一个模型对它们重新排序。PyTorch提供了一个torch.topk函数，它提供了一种方便的方法来获得这些预测。

def predict_topk_nationality(name, classifier, vectorizer, k=5):
    vectorized_name = vectorizer.vectorize(name)
    vectorized_name = torch.tensor(vectorized_name).view(1, -1)
    prediction_vector = classifier(vectorized_name, apply_softmax=True)
    probability_values, indices = torch.topk(prediction_vector, k=k)
    
    # returned size is 1,k
    probability_values = probability_values.detach().numpy()[0]
    indices = indices.detach().numpy()[0]
    
    results = []
    for prob_value, index in zip(probability_values, indices):
        nationality = vectorizer.nationality_vocab.lookup_index(index)
        results.append({'nationality': nationality, 
                        'probability': prob_value})
    
    return results


new_surname = input("Enter a surname to classify: ")
classifier = classifier.to("cpu")

k = int(input("How many of the top predictions to see? "))
if k > len(vectorizer.nationality_vocab):
    print("Sorry! That's more than the # of nationalities we have.. defaulting you to max size :)")
    k = len(vectorizer.nationality_vocab)
    
predictions = predict_topk_nationality(new_surname, classifier, vectorizer, k=k)

print("Top {} predictions:".format(k))
print("===================")
for prediction in predictions:
    print("{} -> {} (p={:0.2f})".format(new_surname,
                                        prediction['nationality'],
                                        prediction['probability']))

推理结果如下：