**Modules**

*None*

**Classes**

**AttentionCellWrapper**:

Basic attention cell wrapper.

**BasicLSTMCell**:

Basic LSTM recurrent network cell.

**BasicRNNCell**:

The most basic RNN cell.

**BidirectionalGridLSTMCell**:

Bidirectional GridLstm cell.

**CompiledWrapper**:

Wraps step execution in an XLA JIT scope.

**Conv1DLSTMCell**:

1D Convolutional LSTM recurrent network cell.

**Conv2DLSTMCell**:

2D Convolutional LSTM recurrent network cell.

**Conv3DLSTMCell**:

3D Convolutional LSTM recurrent network cell.

**ConvLSTMCell**:

Convolutional LSTM recurrent network cell.

**CoupledInputForgetGateLSTMCell**:

Long short-term memory unit (LSTM) recurrent network cell.

**DeviceWrapper**:

Operator that ensures an RNNCell runs on a particular device.

**DropoutWrapper**:

Operator adding dropout to inputs and outputs of the given cell.

**EmbeddingWrapper**:

Operator adding input embedding to the given cell.

**FusedRNNCell**:

Abstract object representing a fused RNN cell.

**FusedRNNCellAdaptor**:

This is an adaptor for RNNCell classes to be used with FusedRNNCell.

**GLSTMCell**:

Group LSTM cell (G-LSTM).

**GRUBlockCell**:

Block GRU cell implementation.

**GRUBlockCellV2**:

Temporary GRUBlockCell impl with a different variable naming scheme.

**GRUCell**:

Gated Recurrent Unit cell (cf. http://arxiv.org/abs/1406.1078).

**GridLSTMCell**:

Grid Long short-term memory unit (LSTM) recurrent network cell.

**HighwayWrapper**:

RNNCell wrapper that adds highway connection on cell input and output.

**InputProjectionWrapper**:

Operator adding an input projection to the given cell.

**IntersectionRNNCell**:

Intersection Recurrent Neural Network (+RNN) cell.

**LSTMBlockCell**:

Basic LSTM recurrent network cell.

**LSTMBlockFusedCell**:

FusedRNNCell implementation of LSTM.

**LSTMBlockWrapper**:

This is a helper class that provides housekeeping for LSTM cells.

**LSTMCell**:

Long short-term memory unit (LSTM) recurrent network cell.

**LSTMStateTuple**:

Tuple used by LSTM Cells for state_size, zero_state, and output state.

**LayerNormBasicLSTMCell**:

LSTM unit with layer normalization and recurrent dropout.

**MultiRNNCell**:

RNN cell composed sequentially of multiple simple cells.

**NASCell**:

Neural Architecture Search (NAS) recurrent network cell.

**OutputProjectionWrapper**:

Operator adding an output projection to the given cell.

**PhasedLSTMCell**:

Phased LSTM recurrent network cell.

**RNNCell**:

Abstract object representing an RNN cell.

**ResidualWrapper**:

RNNCell wrapper that ensures cell inputs are added to the outputs.

**TimeFreqLSTMCell**:

Time-Frequency Long short-term memory unit (LSTM) recurrent network cell.

**TimeReversedFusedRNN**:

This is an adaptor to time-reverse a FusedRNNCell.

**UGRNNCell**:

Update Gate Recurrent Neural Network (UGRNN) cell.

**Functions**

**stack_bidirectional_dynamic_rnn(…)**:

Creates a dynamic bidirectional recurrent neural network.

**stack_bidirectional_rnn(…)**:

Creates a bidirectional recurrent neural network.

**static_bidirectional_rnn(…)**:

Creates a bidirectional recurrent neural network.

**static_rnn(…)**:

Creates a recurrent neural network specified by RNNCell cell.

**static_state_saving_rnn(…)**:

RNN that accepts a state saver for time-truncated RNN calculation.