models/TextCNN.py

# 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/mytrain.txt'                                # 训练集
        self.dev_path = dataset + '/data/mydev.txt'                                    # 验证集
        self.test_path = dataset + '/data/mytest.txt'                                  # 测试集
        self.class_list = [x.strip() for x in open(
            dataset + '/data/myclass.txt', encoding='utf-8').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                                       # 向量预训练词
        #self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')   # 设备
        self.device = torch.device('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 = 512                                           # 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) # 向量预训练词初始化
        else:
            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1) # 向量随机初始化
        # nn.ModuleList,它是一个存储不同module，并自动将每个module的parameters添加到网络之中的容器。
        # 你可以把任意nn.Module的子类（如nn.Conv2d，nn.Linear等）加到这个list里面，
        # 方法和python自带的list一样，如extend，append等操作
        self.convs = nn.ModuleList(
            # 输入通道个数为 1 ，举个例子：如对像素处理中的RGB三原色，因为有三个数，所以是 3 通道
            # 卷积核数量为 256
            # kernel_size：卷积核尺寸  行数分别有 2、3、4 三种，列数都为词向量的维度 是统一的
            [nn.Conv2d(1, config.num_filters, (k, config.embed)) for k in config.filter_sizes])
        # Dropout是为了防止过拟合而设置的
        # Dropout顾名思义有丢掉的意思
        # 表示每个神经元有0.5的可能性不被激活 即不起作用
        self.dropout = nn.Dropout(config.dropout)
        # fc指fully connected，即全连接层 输入神经元为 256*3 输出神经元为 6 （类别数）
        self.fc = nn.Linear(config.num_filters * len(config.filter_sizes), config.num_classes)

    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):
        out = self.embedding(x[0])
        out = out.unsqueeze(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