sundea/text-classification

1# coding: UTF-82import torch3import torch.nn as nn4import torch.nn.functional as F5import numpy as np6 7 8class Config(object):9 10    """配置参数"""11    def __init__(self, dataset, embedding):12        self.model_name = 'TextRCNN'13        self.train_path = dataset + '/data/train.txt'                                # 训练集14        self.dev_path = dataset + '/data/dev.txt'                                    # 验证集15        self.test_path = dataset + '/data/test.txt'                                  # 测试集16        self.class_list = [x.strip() for x in open(17            dataset + '/data/class.txt', encoding='utf-8').readlines()]              # 类别名单18        self.vocab_path = dataset + '/data/vocab.pkl'                                # 词表19        self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt'        # 模型训练结果20        self.log_path = dataset + '/log/' + self.model_name21        self.embedding_pretrained = torch.tensor(22            np.load(dataset + '/data/' + embedding)["embeddings"].astype('float32'))\23            if embedding != 'random' else None                                       # 预训练词向量24        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')   # 设备25 26        self.dropout = 1.0                                              # 随机失活27        self.require_improvement = 1000                                 # 若超过1000batch效果还没提升，则提前结束训练28        self.num_classes = len(self.class_list)                         # 类别数29        self.n_vocab = 0                                                # 词表大小，在运行时赋值30        self.num_epochs = 10                                            # epoch数31        self.batch_size = 128                                           # mini-batch大小32        self.pad_size = 32                                              # 每句话处理成的长度(短填长切)33        self.learning_rate = 1e-3                                       # 学习率34        self.embed = self.embedding_pretrained.size(1)\35            if self.embedding_pretrained is not None else 300           # 字向量维度, 若使用了预训练词向量，则维度统一36        self.hidden_size = 256                                          # lstm隐藏层37        self.num_layers = 1                                             # lstm层数38 39 40'''Recurrent Convolutional Neural Networks for Text Classification'''41 42 43class Model(nn.Module):44    def __init__(self, config):45        super(Model, self).__init__()46        if config.embedding_pretrained is not None:47            self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False)48        else:49            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1)50        self.lstm = nn.LSTM(config.embed, config.hidden_size, config.num_layers,51                            bidirectional=True, batch_first=True, dropout=config.dropout)52        self.maxpool = nn.MaxPool1d(config.pad_size)53        self.fc = nn.Linear(config.hidden_size * 2 + config.embed, config.num_classes)54 55    def forward(self, x):56        x, _ = x57        embed = self.embedding(x)  # [batch_size, seq_len, embeding]=[64, 32, 64]58        out, _ = self.lstm(embed)59        out = torch.cat((embed, out), 2)60        out = F.relu(out)61        out = out.permute(0, 2, 1)62        out = self.maxpool(out).squeeze()63        out = self.fc(out)64        return out65