使用BERT进行情感分析

年前最后一篇，就写个自己使用BERT的流程步骤，提前祝大家新年快乐~

## STEP1：构建模型
class Config(object):
    """配置参数"""

    def __init__(self, dataset):
        self.model_name = 'bert'
        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()]  
        self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt' 
        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')  

        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)  
        self.num_epochs = 3  
        self.batch_size = 128  
        self.pad_size = 32  
        self.learning_rate = 5e-5 
        self.bert_path = './bert_pretrain'
        self.tokenizer = BertTokenizer.from_pretrained(self.bert_path)
        self.hidden_size = 768


class BERT(nn.Module):

    def __init__(self, config):
        super(BERT, self).__init__()
        self.bert = BertModel.from_pretrained(config.bert_path)
        for param in self.bert.parameters():
            param.requires_grad = True
        self.fc = nn.Linear(config.hidden_size, config.num_classes)

    def forward(self, x):
        context = x[0]  # 输入的句子
        mask = x[2]  # 对padding部分进行mask，和句子一个size，padding部分用0表示
        _, pooled = self.bert(context, attention_mask=mask, output_all_encoded_layers=False)
        out = self.fc(pooled)
        return out

## STEP2：构建数据集
def build_dataset(config):
    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')
                tok