rnn and contrib.rnn¶
Build-in recurrent neural network layers are provided in the following two modules:
mxnet.gluon.rnn |
Recurrent neural network module. |
mxnet.gluon.contrib.rnn |
Contrib recurrent neural network module. |
Recurrent Cells¶
rnn.LSTMCell |
Long-Short Term Memory (LSTM) network cell. |
rnn.GRUCell |
Gated Rectified Unit (GRU) network cell. |
rnn.RecurrentCell |
Abstract base class for RNN cells |
rnn.SequentialRNNCell |
Sequentially stacking multiple RNN cells. |
rnn.BidirectionalCell |
Bidirectional RNN cell. |
rnn.DropoutCell |
Applies dropout on input. |
rnn.ZoneoutCell |
Applies Zoneout on base cell. |
rnn.ResidualCell |
Adds residual connection as described in Wu et al, 2016 (https://arxiv.org/abs/1609.08144). |
contrib.rnn.Conv1DRNNCell |
1D Convolutional RNN cell. |
contrib.rnn.Conv2DRNNCell |
2D Convolutional RNN cell. |
contrib.rnn.Conv3DRNNCell |
3D Convolutional RNN cells |
contrib.rnn.Conv1DLSTMCell |
1D Convolutional LSTM network cell. |
contrib.rnn.Conv2DLSTMCell |
2D Convolutional LSTM network cell. |
contrib.rnn.Conv3DLSTMCell |
3D Convolutional LSTM network cell. |
contrib.rnn.Conv1DGRUCell |
1D Convolutional Gated Rectified Unit (GRU) network cell. |
contrib.rnn.Conv2DGRUCell |
2D Convolutional Gated Rectified Unit (GRU) network cell. |
contrib.rnn.Conv3DGRUCell |
3D Convolutional Gated Rectified Unit (GRU) network cell. |
contrib.rnn.VariationalDropoutCell |
Applies Variational Dropout on base cell. |
contrib.rnn.LSTMPCell |
Long-Short Term Memory Projected (LSTMP) network cell. |