cell

Type Members

1. class BasicLSTMCell extends RNNCell[Output, Shape, LSTMState, (Shape, Shape)]

   

   $OpDocRNNCellBasicLSTMCell

2. class BasicRNNCell extends RNNCell[Output, Shape, Output, Shape]

   

   $OpDocRNNCellBasicRNNCell

3. type BasicTuple = ops.rnn.cell.Tuple[ops.Output, ops.Output]

   

4. class DeviceWrapper[O, OS, S, SS] extends RNNCell[O, OS, S, SS]

   

   RNN cell that ensures another RNN cell runs on a specific device.

5. class DropoutWrapper[O, OS, S, SS] extends RNNCell[O, OS, S, SS]

   

   RNN cell that applies dropout to the provided RNN cell.

   RNN cell that applies dropout to the provided RNN cell.

   Note that currently, a different dropout mask is used for each time step in an RNN (i.e., not using the variational recurrent dropout method described in ["A Theoretically Grounded Application of Dropout in Recurrent Neural Networks"](https://arxiv.org/abs/1512.05287).

   Note also that for LSTM cells, no dropout is applied to the memory tensor of the state. It is only applied to the state tensor.

6. class GRUCell extends RNNCell[Output, Shape, Output, Shape]

   

   $OpDocRNNCellGRUCell

7. class LSTMCell extends RNNCell[Output, Shape, LSTMState, (Shape, Shape)]

   

   $OpDocRNNCellLSTMCell

8. type LSTMState = ops.rnn.cell.LSTMState

   

9. type LSTMTuple = ops.rnn.cell.Tuple[ops.Output, ops.rnn.cell.LSTMState]

   

10. class MultiCell[O, OS, S, SS] extends RNNCell[O, OS, Seq[S], Seq[SS]]

    

    RNN cell that is composed by applying a sequence of RNN cells in order.

    RNN cell that is composed by applying a sequence of RNN cells in order.

    This will create a different set of variables for each layer in the stacked LSTM cell (i.e., no variable sharing).

11. abstract class RNNCell[O, OS, S, SS] extends Layer[Tuple[O, S], Tuple[O, S]]

    

12. class ResidualWrapper[O, OS, S, SS] extends RNNCell[O, OS, S, SS]

    

    RNN cell that creates a residual connection (i.e., combining the cell inputs and its outputs) over another RNN cell.

13. type Tuple[O, S] = ops.rnn.cell.Tuple[O, S]