我正在尝试在Tensorflow中实现Bi-MDLSTM(双向多维长期短期记忆),但是我正在努力使我的MDLSTM实现双向。
我正在使用MDLSTM的以下实现:https://github.com/philipperemy/tensorflow-multi-dimensional-lstm
如何在Tensorflow中实现Bi-MDLSTM,我可以做这样的事情吗:
cells = [tf.nn.rnn_cell.MultiDimensionalLSTMCell(numHiddenCells) for _ in range(numOfLayers)]
stacked = tf.nn.rnn_cell.MultiRNNCell(cells, state_is_tuple=True)
((forward, backward), _) = tf.nn.bidirectional_dynamic_rnn(cell_fw=stacked, cell_bw=stacked, inputs=rnnIn3d, dtype=rnnIn3d.dtype)
谢谢您<3