tf.contrib.seq2seq.AttentionWrapperState

View source on GitHub

namedtuple storing the state of a AttentionWrapper.

Contains:

  • cell_state: The state of the wrapped RNNCell at the previous time step.
  • attention: The attention emitted at the previous time step.
  • time: int32 scalar containing the current time step.
  • alignments: A single or tuple of Tensor(s) containing the alignments emitted at the previous time step for each attention mechanism.
  • alignment_history: (if enabled) a single or tuple of TensorArray(s) containing alignment matrices from all time steps for each attention mechanism. Call stack() on each to convert to a Tensor.
  • attention_state: A single or tuple of nested objects containing attention mechanism state for each attention mechanism. The objects may contain Tensors or TensorArrays.

cell_state

attention

time

alignments

alignment_history

attention_state

Methods

clone

View source

Clone this object, overriding components provided by kwargs.

The new state fields' shape must match original state fields' shape. This will be validated, and original fields' shape will be propagated to new fields.

Example:

initial_state = attention_wrapper.zero_state(dtype=..., batch_size=...)
initial_state = initial_state.clone(cell_state=encoder_state)

Args
**kwargs Any properties of the state object to replace in the returned AttentionWrapperState.

Returns
A new AttentionWrapperState whose properties are the same as this one, except any overridden properties as provided in kwargs.