Created by: YelZhang

想使用dynamic_lstm对不定长序列做预测，序列每个pos是一个高维特征list，形如： [ [1,2], [1.2,2.1], [1.3,2.5], ....]
输入这一段要怎么实现

keras的写法很简单：model_2.add(LSTM(dim, activation='relu',input_shape=(n_steps, n_features)))