【注意力机制实例】GeoMAN（二）代码研究

来源：

"""
Yuxuan Liang, Songyu Ke, Junbo Zhang, Xiuwen Yi, Yu Zheng
GeoMAN: Multi-level Attention Networks for Geo-sensory Time Series Prediction
27th International Joint Conference on Artificial Intelligence (IJCAI 2018)
-------------------------------------------------
"""

主要功能由两个文件"GeoMAN.py"和 "base_model.py"实现

模型架构：

base_model.py

计算误差函数：RMSE

def root_mean_squared_error(labels, preds)
def mean_absolute_error(labels, preds)
def mean_squared_error(labels, preds)

待续