知识图谱DKN源码详解（三）config.py

class BaseConfig():
    """
    General configurations appiled to all models
    """
    num_epochs = 2   #迭代次数
    num_batches_show_loss = 100  # Number of batchs to show loss
	num_batches_validate = 1000   # Number of batchs to check metrics on validation dataset
    batch_size = 128          # 一个batch里几个句子
    learning_rate = 0.0001    # 学习率
    num_workers = 4  # Number of workers for data loading  根据你的CPU数量有关
    num_clicked_news_a_user = 50  # Number of sampled click history for each user
    num_words_title = 20  #一个标题有几个单词
    num_words_abstract = 50  #一个摘要有多少个单词
    word_freq_threshold = 1  #单词频度的阈值，多少才能认为是感兴趣的单词
    entity_freq_threshold = 2  #实体频度阈值，多少才能认为是感兴趣的实体
    entity_confidence_threshold = 0.5  #实体置信度阈值，多少才能被认为是有用的实体
    negative_sampling_ratio = 2  # K  #消极样本取样率
    dropout_probability = 0.2     #dropout 防止过拟合
    # Modify the following by the output of `src/dataprocess.py`
    num_words = 1 + 101220   #单词量
    num_categories = 1 + 295 #类别数量
    num_entities = 1 + 21842  #实体数量
    num_users = 1 + 711222   #用户数量
    word_embedding_dim = 300  #单词嵌入维度
    category_embedding_dim = 100  #类别嵌入维度
    # Modify the following only if you use another dataset
    entity_embedding_dim = 100  #实体嵌入维度
    # For additive attention
    query_vector_dim = 200   #查询向量维度