Advertisement

lstm调参之旅一:dim_proj–validFreq–saveFreq–maxlen–valid_batch_size–modal_costs–recyl_maxlen

阅读量:
  • dim_proj:用于表征特征类型的数量
    • validFreq:定义在进行多少次参数更新后执行验证误差计算
    • saveFreq:在每次完成saveFreq次参数更新时进行模型参数保存,表示参数保存的频率
    • maxlen:通常应与模态数目保持一致
    • valid_batch_size:测试数据的批量大小,必须小于测试集的总样本数
    • modal_costs:一个一维矩阵,其元素个数等于模态的数量
复制代码
 def train_lstm(

    
     dim_proj=72,  # word embeding dimension and LSTM number of hidden units.
    
     patience=15,  # Number of epoch to wait before early stop if no progress
    
     max_epochs=5000,  # The maximum number of epoch to run
    
     dispFreq=10,  # Display to stdout the training progress every N updates
    
     decay_c=0.,  # Weight decay fo

全部评论 (0)

还没有任何评论哟~