【LSTM新闻数据集分类代码】

• rnn

import time
import torch
import numpy as np
from train_eval import train, init_network
from importlib import import_module
import argparse#命令行解析，当代码需要频繁修改参数时用，让参数与代码分离，代码更加简洁
from tensorboardX import SummaryWriter
#--model=TextRNN
parser = argparse.ArgumentParser(description='Chinese Text Classification')
parser.add_argument('--model', type=str, required=True, help='choose a model: TextCNN, TextRNN, FastText, TextRCNN, TextRNN_Att, DPCNN, Transformer')
parser.add_argument('--embedding', default='pre_trained', type=str, help='random or pre_trained')
parser.add_argument('--word', default=False, type=bool, help='True for word, False for char')
#parser.add_argument()里面的参数:第一个是参数名称，type参数类型，default参数的默认值，
# help帮助信息
args = parser.parse_args()#解析参数，可以从args中获取对应参数的对应值


if __name__ == '__main__':#如果为主程序就执行后面程序，如果在其他文件调用run.py这个文件就不执行后面程序
    dataset = 'THUCNews'  # 数据集

    # 搜狗新闻:embedding_SougouNews.npz, 腾讯:embedding_Tencent.npz, 随机初始化:random
    embedding = 'embedding_SougouNews.npz'#用了别人训练好的,把每个字转化成一个向量，不用自己做训练了(这里只是个分类任务)
    if args.embedding == 'random':
        embedding = 'random'
    model_name = args.model  #选择用那个模型TextCNN, TextRNN,一开始参数配置的时候就选了
    if model_name == 'FastText':
        from utils_fasttext import build_dataset, build_iterator, get_time_dif
        embedding = 'random'
    else:
        from utils import build_dataset, build_iterator, get_time_dif

    x = import_module('models.' + model_name)#把你选的模块导入进来
    config = x.Config(dataset, embedding)#配置文件
    np.random.seed(1)
    torch.manual_seed(1)
    torch.cuda.manual_seed_all(1)
    torch.backends.cudnn.deterministic = True  #每次随机初始化的时候结果都是一样的
    #在训练过程中可能会取调节各种网络结构或者参数，只有保证每次初始化策略都是一样的才能看出来一些具体参数的影响


    start_time = time.time()
    print("Loading data...")#后面几行是把数据读进来
    vocab, train_data, dev_data, test_data = build_dataset(config, args.word)#这行是把数据都读进来，这些数据都是每个字对应的索引了
    train_iter = build_iterator(train_data, config)
    dev_iter = build_iterator(dev_data, config)
    test_iter = build_iterator(test_data, config)#这三行把每一个batch拿到手
    time_dif = get_time_dif(start_time)#算一下我在读数据上的用时
    print("Time usage:", time_dif)

    # train
    config.n_vocab = len(vocab)
    model = x.Model(config).to(config.device)
    writer = SummaryWriter(log_dir=config.log_path + '/' + time.strftime('%m-%d_%H.%M', time.localtime()))
    if model_name != 'Transformer':
        init_network(model)#权重参数初始化
    print(model.parameters)#打印模型的结构
    train(config, model, train_iter, dev_iter, test_iter,writer)#训练模块

• train_eval

# coding: UTF-8
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from sklearn import metrics
import time
from utils import get_time_dif
from tensorboardX import SummaryWriter


# 权重初始化，默认xavier
def init_network(model, method='xavier', exclude='embedding', seed=123):#权重参数初始化
    for name, w in model.named_parameters():
        if exclude not in name:
            if 'weight' in name:
                if method == 'xavier':
                    nn.init.xavier_normal_(w)
                elif method == 'kaiming':
                    nn.init.kaiming_normal_(w)
                else:
                    nn.init.normal_(w)
            elif 'bias' in name:
                nn.init.constant_(w, 0)
            else:
                pass


def train(config, model, train_iter, dev_iter, test_iter,writer):
    start_time = time.time()
    model.train()# model.train()将启用BatchNormalization和Dropout,归一化和随机失活
    # 相应的model.eval()则不启用BatchNormalization和Dropout
    optimizer = torch.optim.Adam(model.parameters(), lr=config.learning_rate)#指定优化方法

    # 学习率指数衰减，每次epoch：学习率 = gamma * 学习率
    # scheduler = torch.optim.lr_scheduler.ExponentialLR(optimizer, gamma=0.9)
    total_batch = 0  # 记录进行到多少batch
    dev_best_loss = float('inf')#记录当前最好的损失是多少，一开始设置成无穷大最后慢慢选
    last_improve = 0  # 记录上次验证集loss下降的batch数
    flag = False  # 记录是否很久没有效果提升
    #writer = SummaryWriter(log_dir=config.log_path + '/' + time.strftime('%m-%d_%H.%M', time.localtime()))#用来可视化展示的
    for epoch in range(config.num_epochs):
        print('Epoch [{}/{}]'.format(epoch + 1, config.num_epochs))
        # scheduler.step() # 学习率衰减
        for i, (trains, labels) in enumerate(train_iter):
            #print (trains[0].shape)
            outputs = model(trains)#前向传播
            model.zero_grad()#梯度清零
            loss = F.cross_entropy(outputs, labels)#计算损失函数
            loss.backward()#反向传播
            optimizer.step()
            if total_batch % 100 == 0:
                # 每多少轮输出在训练集和验证集上的效果
                true = labels.data.cpu()
                predic = torch.max(outputs.data, 1)[1].cpu()
                train_acc = metrics.accuracy_score(true, predic)#计算准确率
                dev_acc, dev_loss = evaluate(config, model, dev_iter)#计算验证集的准确率和损失值
                if dev_loss < dev_best_loss:
                    dev_best_loss = dev_loss
                    torch.save(model.state_dict(), config.save_path)#比之前好就保存
                    improve = '*'
                    last_improve = total_batch
                else:
                    improve = ''
                time_dif = get_time_dif(start_time)
                msg = 'Iter: {0:>6},  Train Loss: {1:>5.2},  Train Acc: {2:>6.2%},  Val Loss: {3:>5.2},  Val Acc: {4:>6.2%},  Time: {5} {6}'
                print(msg.format(total_batch, loss.item(), train_acc, dev_loss, dev_acc, time_dif, improve))
                writer.add_scalar("loss/train", loss.item(), total_batch)
                writer.add_scalar("loss/dev", dev_loss, total_batch)
                writer.add_scalar("acc/train", train_acc, total_batch)
                writer.add_scalar("acc/dev", dev_acc, total_batch)#这几个主要是记录训练集损失，验证集损失，以及准确率等都保存在的指定路径下
                model.train()
            total_batch += 1
            if total_batch - last_improve > config.require_improvement:
                # 验证集loss超过1000batch没下降，结束训练
                print("No optimization for a long time, auto-stopping...")
                flag = True
                break
        if flag:
            break
    writer.close()
    test(config, model, test_iter)


def test(config, model, test_iter):
    # test
    model.load_state_dict(torch.load(config.save_path))
    model.eval()
    start_time = time.time()
    test_acc, test_loss, test_report, test_confusion = evaluate(config, model, test_iter, test=True)
    msg = 'Test Loss: {0:>5.2},  Test Acc: {1:>6.2%}'
    print(msg.format(test_loss, test_acc))
    print("Precision, Recall and F1-Score...")
    print(test_report)
    print("Confusion Matrix...")
    print(test_confusion)
    time_dif = get_time_dif(start_time)
    print("Time usage:", time_dif)


def evaluate(config, model, data_iter, test=False):
    model.eval()
    loss_total = 0
    predict_all = np.array([], dtype=int)
    labels_all = np.array([], dtype=int)
    with torch.no_grad():#验证集里不做任何更新
        for texts, labels in data_iter:
            outputs = model(texts)#得到预测结果
            loss = F.cross_entropy(outputs, labels)#计算损失
            loss_total += loss
            labels = labels.data.cpu().numpy()
            predic = torch.max(outputs.data, 1)[1].cpu().numpy()
            labels_all = np.append(labels_all, labels)
            predict_all = np.append(predict_all, predic)

    acc = metrics.accuracy_score(labels_all, predict_all)#把每个batch的结构都拿到手之后最后一起算准确率
    if test:
        report = metrics.classification_report(labels_all, predict_all, target_names=config.class_list, digits=4)
        confusion = metrics.confusion_matrix(labels_all, predict_all)
        return acc, loss_total / len(data_iter), report, confusion
    return acc, loss_total / len(data_iter)

• utils

# coding: UTF-8
import os
import torch
import numpy as np
import pickle as pkl
from tqdm import tqdm
import time
from datetime import timedelta


MAX_VOCAB_SIZE = 10000  # 词表长度限制
UNK, PAD = '<UNK>', '<PAD>'  # 未知字，padding符号


def build_vocab(file_path, tokenizer, max_size, min_freq):
    vocab_dic = {}
    with open(file_path, 'r', encoding='UTF-8') as f:
        for line in tqdm(f):
            lin = line.strip()
            if not lin:
                continue
            content = lin.split('\t')[0]
            for word in tokenizer(content):
                vocab_dic[word] = vocab_dic.get(word, 0) + 1
        vocab_list = sorted([_ for _ in vocab_dic.items() if _[1] >= min_freq], key=lambda x: x[1], reverse=True)[:max_size]
        vocab_dic = {word_count[0]: idx for idx, word_count in enumerate(vocab_list)}
        vocab_dic.update({UNK: len(vocab_dic), PAD: len(vocab_dic) + 1})
    return vocab_dic


def build_dataset(config, ues_word):
    if ues_word:#具体用词组还是字切分可以选
        tokenizer = lambda x: x.split(' ')  #把每个字以空格隔开，word-level，
    else:
        tokenizer = lambda x: [y for y in x]  # char-level
    if os.path.exists(config.vocab_path):
        vocab = pkl.load(open(config.vocab_path, 'rb'))
    else:
        vocab = build_vocab(config.train_path, tokenizer=tokenizer, max_size=MAX_VOCAB_SIZE, min_freq=1)
        pkl.dump(vocab, open(config.vocab_path, 'wb'))
    print(f"Vocab size: {len(vocab)}")

    def load_dataset(path, pad_size=32):
        contents = []
        with open(path, 'r', encoding='UTF-8') as f:
            for line in tqdm(f):
                lin = line.strip()
                if not lin:
                    continue
                content, label = lin.split('\t')#把数据切分，因为数据里面前面的汉字是样本，后面的数字是标签
                words_line = []
                token = tokenizer(content)#tokenizer把这句话拆成一个一个的字
                seq_len = len(token)#看一下多长后边多切断补
                if pad_size:
                    if len(token) < pad_size:
                        token.extend([vocab.get(PAD)] * (pad_size - len(token)))#这里当长度不够的时候填充的是一个特殊字符PAD对应的索引
                    else:
                        token = token[:pad_size]
                        seq_len = pad_size
                # word to id
                for word in token:
                    words_line.append(vocab.get(word, vocab.get(UNK)))#把每个切分好的字传进去然后输出每个字对应的索引
                contents.append((words_line, int(label), seq_len))#这里就都是每次字对应的索引了
        return contents  # [([...], 0), ([...], 1), ...]
    train = load_dataset(config.train_path, config.pad_size)#读取进来训练集
    dev = load_dataset(config.dev_path, config.pad_size)#读取验证集
    test = load_dataset(config.test_path, config.pad_size)#读取测试集
    return vocab, train, dev, test


class DatasetIterater(object):
    def __init__(self, batches, batch_size, device):
        self.batch_size = batch_size
        self.batches = batches
        self.n_batches = len(batches) // batch_size
        self.residue = False  # 记录batch数量是否为整数
        if len(batches) % self.n_batches != 0:
            self.residue = True
        self.index = 0
        self.device = device

    def _to_tensor(self, datas):
        x = torch.LongTensor([_[0] for _ in datas]).to(self.device)
        y = torch.LongTensor([_[1] for _ in datas]).to(self.device)

        # pad前的长度(超过pad_size的设为pad_size)
        seq_len = torch.LongTensor([_[2] for _ in datas]).to(self.device)
        return (x, seq_len), y

    def __next__(self):
        if self.residue and self.index == self.n_batches:
            batches = self.batches[self.index * self.batch_size: len(self.batches)]
            self.index += 1
            batches = self._to_tensor(batches)
            return batches

        elif self.index > self.n_batches:
            self.index = 0
            raise StopIteration
        else:
            batches = self.batches[self.index * self.batch_size: (self.index + 1) * self.batch_size]
            self.index += 1
            batches = self._to_tensor(batches)
            return batches

    def __iter__(self):
        return self

    def __len__(self):
        if self.residue:
            return self.n_batches + 1
        else:
            return self.n_batches


def build_iterator(dataset, config):
    iter = DatasetIterater(dataset, config.batch_size, config.device)
    return iter


def get_time_dif(start_time):
    """获取已使用时间"""
    end_time = time.time()
    time_dif = end_time - start_time
    return timedelta(seconds=int(round(time_dif)))


if __name__ == "__main__":
    '''提取预训练词向量'''
    # 下面的目录、文件名按需更改。
    train_dir = "./THUCNews/data/train.txt"
    vocab_dir = "./THUCNews/data/vocab.pkl"
    pretrain_dir = "./THUCNews/data/sgns.sogou.char"
    emb_dim = 300
    filename_trimmed_dir = "./THUCNews/data/embedding_SougouNews"
    if os.path.exists(vocab_dir):
        word_to_id = pkl.load(open(vocab_dir, 'rb'))
    else:
        # tokenizer = lambda x: x.split(' ')  # 以词为单位构建词表(数据集中词之间以空格隔开)
        tokenizer = lambda x: [y for y in x]  # 以字为单位构建词表
        word_to_id = build_vocab(train_dir, tokenizer=tokenizer, max_size=MAX_VOCAB_SIZE, min_freq=1)
        pkl.dump(word_to_id, open(vocab_dir, 'wb'))

    embeddings = np.random.rand(len(word_to_id), emb_dim)
    f = open(pretrain_dir, "r", encoding='UTF-8')
    for i, line in enumerate(f.readlines()):
        # if i == 0:  # 若第一行是标题，则跳过
        #     continue
        lin = line.strip().split(" ")
        if lin[0] in word_to_id:
            idx = word_to_id[lin[0]]
            emb = [float(x) for x in lin[1:301]]
            embeddings[idx] = np.asarray(emb, dtype='float32')
    f.close()
    np.savez_compressed(filename_trimmed_dir, embeddings=embeddings)

• utils_fasttext

# coding: UTF-8
import os
import torch
import numpy as np
import pickle as pkl
from tqdm import tqdm
import time
from datetime import timedelta


MAX_VOCAB_SIZE = 10000
UNK, PAD = '<UNK>', '<PAD>'


def build_vocab(file_path, tokenizer, max_size, min_freq):
    vocab_dic = {}
    with open(file_path, 'r', encoding='UTF-8') as f:
        for line in tqdm(f):
            lin = line.strip()
            if not lin:
                continue
            content = lin.split('\t')[0]
            for word in tokenizer(content):
                vocab_dic[word] = vocab_dic.get(word, 0) + 1
        vocab_list = sorted([_ for _ in vocab_dic.items() if _[1] >= min_freq], key=lambda x: x[1], reverse=True)[:max_size]
        vocab_dic = {word_count[0]: idx for idx, word_count in enumerate(vocab_list)}
        vocab_dic.update({UNK: len(vocab_dic), PAD: len(vocab_dic) + 1})
    return vocab_dic


def build_dataset(config, ues_word):
    if ues_word:
        tokenizer = lambda x: x.split(' ')  # 以空格隔开，word-level
    else:
        tokenizer = lambda x: [y for y in x]  # char-level
    if os.path.exists(config.vocab_path):
        vocab = pkl.load(open(config.vocab_path, 'rb'))
    else:
        vocab = build_vocab(config.train_path, tokenizer=tokenizer, max_size=MAX_VOCAB_SIZE, min_freq=1)
        pkl.dump(vocab, open(config.vocab_path, 'wb'))
    print(f"Vocab size: {len(vocab)}")

    def biGramHash(sequence, t, buckets):
        t1 = sequence[t - 1] if t - 1 >= 0 else 0
        return (t1 * 14918087) % buckets

    def triGramHash(sequence, t, buckets):
        t1 = sequence[t - 1] if t - 1 >= 0 else 0
        t2 = sequence[t - 2] if t - 2 >= 0 else 0
        return (t2 * 14918087 * 18408749 + t1 * 14918087) % buckets

    def load_dataset(path, pad_size=32):
        contents = []
        with open(path, 'r', encoding='UTF-8') as f:
            for line in tqdm(f):
                lin = line.strip()
                if not lin:
                    continue
                content, label = lin.split('\t')
                words_line = []
                token = tokenizer(content)
                seq_len = len(token)
                if pad_size:
                    if len(token) < pad_size:
                        token.extend([vocab.get(PAD)] * (pad_size - len(token)))
                    else:
                        token = token[:pad_size]
                        seq_len = pad_size
                # word to id
                for word in token:
                    words_line.append(vocab.get(word, vocab.get(UNK)))

                # fasttext ngram
                buckets = config.n_gram_vocab
                bigram = []
                trigram = []
                # ------ngram------
                for i in range(pad_size):
                    bigram.append(biGramHash(words_line, i, buckets))
                    trigram.append(triGramHash(words_line, i, buckets))
                # -----------------
                contents.append((words_line, int(label), seq_len, bigram, trigram))
        return contents  # [([...], 0), ([...], 1), ...]
    train = load_dataset(config.train_path, config.pad_size)
    dev = load_dataset(config.dev_path, config.pad_size)
    test = load_dataset(config.test_path, config.pad_size)
    return vocab, train, dev, test


class DatasetIterater(object):
    def __init__(self, batches, batch_size, device):
        self.batch_size = batch_size
        self.batches = batches
        self.n_batches = len(batches) // batch_size
        self.residue = False  # 记录batch数量是否为整数 
        if len(batches) % self.n_batches != 0:
            self.residue = True
        self.index = 0
        self.device = device

    def _to_tensor(self, datas):
        # xx = [xxx[2] for xxx in datas]
        # indexx = np.argsort(xx)[::-1]
        # datas = np.array(datas)[indexx]
        x = torch.LongTensor([_[0] for _ in datas]).to(self.device)
        y = torch.LongTensor([_[1] for _ in datas]).to(self.device)
        bigram = torch.LongTensor([_[3] for _ in datas]).to(self.device)
        trigram = torch.LongTensor([_[4] for _ in datas]).to(self.device)

        # pad前的长度(超过pad_size的设为pad_size)
        seq_len = torch.LongTensor([_[2] for _ in datas]).to(self.device)
        return (x, seq_len, bigram, trigram), y

    def __next__(self):
        if self.residue and self.index == self.n_batches:
            batches = self.batches[self.index * self.batch_size: len(self.batches)]
            self.index += 1
            batches = self._to_tensor(batches)
            return batches

        elif self.index > self.n_batches:
            self.index = 0
            raise StopIteration
        else:
            batches = self.batches[self.index * self.batch_size: (self.index + 1) * self.batch_size]
            self.index += 1
            batches = self._to_tensor(batches)
            return batches

    def __iter__(self):
        return self

    def __len__(self):
        if self.residue:
            return self.n_batches + 1
        else:
            return self.n_batches


def build_iterator(dataset, config):
    iter = DatasetIterater(dataset, config.batch_size, config.device)
    return iter


def get_time_dif(start_time):
    """获取已使用时间"""
    end_time = time.time()
    time_dif = end_time - start_time
    return timedelta(seconds=int(round(time_dif)))

if __name__ == "__main__":
    '''提取预训练词向量'''
    vocab_dir = "./THUCNews/data/vocab.pkl"
    pretrain_dir = "./THUCNews/data/sgns.sogou.char"
    emb_dim = 300
    filename_trimmed_dir = "./THUCNews/data/vocab.embedding.sougou"
    word_to_id = pkl.load(open(vocab_dir, 'rb'))
    embeddings = np.random.rand(len(word_to_id), emb_dim)
    f = open(pretrain_dir, "r", encoding='UTF-8')
    for i, line in enumerate(f.readlines()):
        # if i == 0:  # 若第一行是标题，则跳过
        #     continue
        lin = line.strip().split(" ")
        if lin[0] in word_to_id:
            idx = word_to_id[lin[0]]
            emb = [float(x) for x in lin[1:301]]
            embeddings[idx] = np.asarray(emb, dtype='float32')
    f.close()
    np.savez_compressed(filename_trimmed_dir, embeddings=embeddings)

• TextRNN

# coding: UTF-8
import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np


class Config(object):

    """配置参数"""
    def __init__(self, dataset, embedding):
        self.model_name = 'TextRNN'
        self.train_path = dataset + '/data/train.txt' # 训练集路径
        self.dev_path = dataset + '/data/dev.txt'     # 验证集
        self.test_path = dataset + '/data/test.txt'   # 测试集
        self.class_list = [x.strip() for x in open(
            dataset + '/data/class.txt').readlines()] #10个类别名单
        self.vocab_path = dataset + '/data/vocab.pkl' #词表里面是每一个词及其对应的索引，词嵌入的查找是基于这个索引来找对应的词的词向量表示
        self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt' #模型训练结果，指定保存路径
        self.log_path = dataset + '/log/' + self.model_name#把中间的一些比如中间的损失保存下来可以做可视化展示
        self.embedding_pretrained = torch.tensor(#把提供的别人训练好的模型里面的词向量读进来再转化成tensor的格式
            np.load(dataset + '/data/' + embedding)["embeddings"].astype('float32'))\
            if embedding != 'random' else None                                       # 预训练词向量
        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')   # 指定设备，我这没有gpu用cpu跑的

        self.dropout = 0.5                                   # 随机失活，防止过拟合
        self.require_improvement = 1000                      # 若超过1000batch效果还没提升，则提前结束训练
        self.num_classes = len(self.class_list)              # 类别数有10个类别
        self.n_vocab = 0                                     # 词表大小，在运行时赋值，实际把词表读进来之后再赋值
        self.num_epochs = 10                                 # epoch数
        self.batch_size = 128                                # mini-batch大小
        self.pad_size = 32                                   # 每句话处理成的长度(短填长切)
        self.learning_rate = 1e-3                            # 学习率
        self.embed = self.embedding_pretrained.size(1)\
            if self.embedding_pretrained is not None else 300 # 字向量维度,用的人家的词表那就根据他的维度，是300
        self.hidden_size = 128                                # lstm隐藏层神经元个数
        self.num_layers = 2                                   # lstm层数


'''Recurrent Neural Network for Text Classification with Multi-Task Learning'''


class Model(nn.Module):
    def __init__(self, config):
        super(Model, self).__init__()
        if config.embedding_pretrained is not None:#nn.Embedding作用就是把每个词都转化成对应的词向量(实际是通过索引做的)
            self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False)
        else:
            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1)
        self.lstm = nn.LSTM(config.embed, config.hidden_size, config.num_layers,
                            bidirectional=True, batch_first=True, dropout=config.dropout)
        #LSTM的几个输入的意思:config.embed是当前输入的特征也就是300维，config.hidden_size隐藏层神经元128个就是每一个x0进入A得到一个中间结果h0过程中A的神经元个数
        #config.num_layers指LSTM的层数一般取最后一层的最后一个输出，bidirectional=True代表LSTM是双向的(效果好)，batch_first=True指定第一个维度是batch
        #dropout=config.dropout随机失活
        self.fc = nn.Linear(config.hidden_size * 2, config.num_classes)#最后的全连接层因为是双向的所以要乘以2，
        # 这里全连接层连接的是最后一层LSTM的最后一个输出，然后转化成10个类别

    def forward(self, x):
        x, _ = x
        out = self.embedding(x)  # 先走一个embedding层[batch_size, seq_len, embeding]=[128, 32, 300]
        out, _ = self.lstm(out)#在经过letm层
        out = self.fc(out[:, -1, :])  # 把最后一层的最后一个时刻的输出丢到全连接层里面
        # hidden state，out[:, -1, :]代表的是取LSTM的最后一个隐层特征(256)丢到全连接层里面
        return out

• TextCNN

# coding: UTF-8
import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np


class Config(object):

    """配置参数"""
    def __init__(self, dataset, embedding):
        self.model_name = 'TextCNN'
        self.train_path = dataset + '/data/train.txt'                                # 训练集
        self.dev_path = dataset + '/data/dev.txt'                                    # 验证集
        self.test_path = dataset + '/data/test.txt'                                  # 测试集
        self.class_list = [x.strip() for x in open(
            dataset + '/data/class.txt').readlines()]                                # 类别名单
        self.vocab_path = dataset + '/data/vocab.pkl'                                # 词表
        self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt'        # 模型训练结果
        self.log_path = dataset + '/log/' + self.model_name
        self.embedding_pretrained = torch.tensor(
            np.load(dataset + '/data/' + embedding)["embeddings"].astype('float32'))\
            if embedding != 'random' else None                                       # 预训练词向量
        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')   # 设备

        self.dropout = 0.5                                              # 随机失活
        self.require_improvement = 1000                                 # 若超过1000batch效果还没提升，则提前结束训练
        self.num_classes = len(self.class_list)                         # 类别数
        self.n_vocab = 0                                                # 词表大小，在运行时赋值
        self.num_epochs = 20                                            # epoch数
        self.batch_size = 128                                           # mini-batch大小
        self.pad_size = 32                                              # 每句话处理成的长度(短填长切)
        self.learning_rate = 1e-3                                       # 学习率
        self.embed = self.embedding_pretrained.size(1)\
            if self.embedding_pretrained is not None else 300           # 字向量维度
        self.filter_sizes = (2, 3, 4)                                   # 卷积核尺寸
        self.num_filters = 256                                          # 卷积核数量(channels数)


'''Convolutional Neural Networks for Sentence Classification'''


class Model(nn.Module):
    def __init__(self, config):
        super(Model, self).__init__()
        if config.embedding_pretrained is not None:
            self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False)
        else:
            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1)
        self.convs = nn.ModuleList(#你后边有3个卷积核，要转成ModuleList才行
            [nn.Conv2d(1, config.num_filters, (k, config.embed)) for k in config.filter_sizes])#卷积核的大小是不同的，
        # 这里用了个循环(k, config.embed)是卷积核的维度，k分别为2，3，4，config.embed是300维的
        self.dropout = nn.Dropout(config.dropout)
        self.fc = nn.Linear(config.num_filters * len(config.filter_sizes), config.num_classes)
        #config.num_classes就是10，config.num_filters代表的是你卷积之后每个卷积核都得到的256个特征图特征图，也就是我每个卷积层用来256个卷积核，
        # 所以特征图数量是265*3，那池话之后也是256*3这么多特征个数

    def conv_and_pool(self, x, conv):
        x = F.relu(conv(x)).squeeze(3)
        x = F.max_pool1d(x, x.size(2)).squeeze(2)
        return x

    def forward(self, x):
        #print (x[0].shape)
        out = self.embedding(x[0])
        out = out.unsqueeze(1)#加了一个颜色通道，就是1
        out = torch.cat([self.conv_and_pool(out, conv) for conv in self.convs], 1)
        out = self.dropout(out)
        out = self.fc(out)
        return out