Python tf.keras.layers.StackedRNNCells用法及代码示例

Wrapper 允许一堆 RNN 单元格作为单个单元格运行。

继承自：Layer，Module

用法

tf.keras.layers.StackedRNNCells(
    cells, **kwargs
)

用于实现高效的堆叠 RNN。

例子：

batch_size = 3
sentence_max_length = 5
n_features = 2
new_shape = (batch_size, sentence_max_length, n_features)
x = tf.constant(np.reshape(np.arange(30), new_shape), dtype = tf.float32)

rnn_cells = [tf.keras.layers.LSTMCell(128) for _ in range(2)]
stacked_lstm = tf.keras.layers.StackedRNNCells(rnn_cells)
lstm_layer = tf.keras.layers.RNN(stacked_lstm)

result = lstm_layer(x)