State of a tfa.seq2seq.BeamSearchDecoder
.
tfa.seq2seq.BeamSearchDecoderState(
cell_state, log_probs, finished, lengths, accumulated_attention_probs
)
Attributes |
cell_state
|
The cell state returned at the previous time step.
|
log_probs
|
The accumulated log probabilities of each beam.
A float32 Tensor of shape [batch_size, beam_width] .
|
finished
|
The finished status of each beam.
A bool Tensor of shape [batch_size, beam_width] .
|
lengths
|
The accumulated length of each beam.
An int64 Tensor of shape [batch_size, beam_width] .
|
accumulated_attention_probs
|
A namedtuple alias for field number 4
|
accumulated_attention_prob
|
Accumulation of the attention
probabilities (used to compute the coverage penalty)
|