nabu.neuralnetworks.components.beam_search_decoder.BeamSearchDecoder Class Reference

the beam search decode More...

Inheritance diagram for nabu.neuralnetworks.components.beam_search_decoder.BeamSearchDecoder:

Public Member Functions
def	batch_size (self)
	the batch size
def	output_size (self)
	the output size (empty)
def	output_dtype (self)
	the output dtype (empty)
def	__init__ (self, cell, embedding, start_tokens, end_token, initial_state, beam_width, output_layer=None, length_penalty_weight=0.0, temperature=1.0)
	constructor More...
def	initialize (self, name=None)
	Called before any decoding iterations. More...
def	step (self, time, inputs, state, name=None)
	Called per step of decoding (but only once for dynamic decoding). More...
def	finalize (self, outputs, final_state, sequence_lengths)
	Finalize and return the predicted_ids. More...

Public Attributes
	cell
	embedding
	start_tokens
	end_token
	initial_state
	beam_width
	output_layer
	length_penalty_weight

Detailed Description

the beam search decode

Constructor & Destructor Documentation

__init__()

def nabu.neuralnetworks.components.beam_search_decoder.BeamSearchDecoder.__init__	(		self,
			cell,
			embedding,
			start_tokens,
			end_token,
			initial_state,
			beam_width,
			output_layer = None,
			length_penalty_weight = 0.0,
			temperature = 1.0
	)

constructor

Parameters

cell	An RNNCell instance.
embedding	A callable that takes a vector tensor of ids (argmax ids), or the params argument for embedding_lookup.
start_tokens	int32 vector shaped [batch_size], the start
tokens.
end_token	int32 scalar, the token that marks end of decoding.
initial_state	A (possibly nested tuple of...) tensors and
TensorArrays.
beam_width	Python integer, the number of beams.
output_layer	(Optional) An instance of tf.layers.Layer, i.e., tf.layers.Dense. Optional layer to apply to the RNN output prior to storing the result or sampling.
length_penalty_weight	Float weight to penalize length. Disabled with 0.0.
temperature	a temperature to apply before the softmax to smooth or sharpen the probabilities. High temperature means a smooth
distribution

Member Function Documentation

finalize()

def nabu.neuralnetworks.components.beam_search_decoder.BeamSearchDecoder.finalize	(		self,
			outputs,
			final_state,
			sequence_lengths
	)

Finalize and return the predicted_ids.

Parameters

outputs	An instance of BeamSearchDecoderOutput.
final_state	An instance of BeamSearchState.
sequence_lengths	An int64 tensor shaped [batch_size, beam_width]. The sequence lengths

Returns

• An instance of BeamSearchDecoderFinalOutput
• The final state

initialize()

def nabu.neuralnetworks.components.beam_search_decoder.BeamSearchDecoder.initialize	(		self,
			name = None
	)

Called before any decoding iterations.

This methods must compute initial input values and initial state.

Parameters

name	Name scope for any created operations.

Returns

(finished, initial_inputs, initial_state): initial values of 'finished' flags, inputs and state.

step()

def nabu.neuralnetworks.components.beam_search_decoder.BeamSearchDecoder.step	(		self,
			time,
			inputs,
			state,
			name = None
	)

Called per step of decoding (but only once for dynamic decoding).

Parameters

time	Scalar int32 tensor. Current step number.
inputs	RNNCell input (possibly nested tuple of) tensor[s] for this time step.
state	RNNCell state (possibly nested tuple of) tensor[s] from previous time step.
name	Name scope for any created operations.

Returns

(outputs, next_state, next_inputs, finished): outputs is an object containing the decoder output, next_state is a (structure of) state tensors and TensorArrays, next_inputs is the tensor that should be used as input for the next step, finished is a boolean tensor telling whether the sequence is complete, for each sequence in the batch.

---

The documentation for this class was generated from the following file:

• components/beam_search_decoder.py