在Tensorflow教程中,我正在实验LSTM时间序列由于这里的任务比以前的任务要复杂一些,所以模型现在由两个LSTM层组成。然后,从实现的角度,使用Python库,multi_step_model.add(tf.keras.layers.LSTMinput_shape=x_train_multi.shape[-2:]))
m
__init__ (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version__init__ (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future versionWARNING: bidirectional_dynamic_rnn (from tensorflow.python.ops.