Initializes the generator. Args: model: recurrent model, with inputs: (input, state) and outputs len(vocab) values beam_size: Beam size to use when generating captions. max_caption_length: The maximum caption length before stopping the search. length_
(self,
embedder,
rnn,
classifier,
eos_id,
beam_size=1,
max_caption_length=20,
length_normalization_factor=0.0)
source not stored for this graph (policy: none)
nothing calls this directly
no outgoing calls
no test coverage detected