Feeds an image and returns the initial model state. See comments at the top of file. Args: sess: TensorFlow Session object. enco

Returns the word string of an integer word id.

Runs one step of inference. Args: sess: TensorFlow Session object. input_feed: A numpy array of shape [batch_size]. state_feed:

Evaluate predicted_file and return mAP.

Convert annotation JSON file.

Convert prediction JSON file.

Load personalized dict to improve detect rate. Parameter: - f : A plain text file contains words and their ocurrences.

The evaluator.

The evaluator.

Calculates longest common subsequence for a pair of tokenized strings :param string : list of str : tokens from a string split using whitespa

Returns the TopN to an empty state.

return (bleu, len_ratio) pair

Sets up the global step Tensor.

Sets up the function to restore inception variables from checkpoint.

Suggest word frequency to force the characters in a word to be joined or splitted. Parameter: - segment : The se

Tokenize a sentence and yields tuples of (word, start, end) Parameter: - sentence: the str(unicode) to be segmented.

Returns the integer id of a word string.

Compares Captions by score.

add an instance (e.g., from another sentence).

add an instance (e.g., from another sentence).

Initializes the vocabulary. Args: vocab: A dictionary of word to word_id. unk_id: Id of the special 'unknown' word.

Sets the default model hyperparameters.

Sets the default training hyperparameters.

Basic setup. Args: config: Object containing configuration parameters. mode: "train", "eval" or "inference". train_inception: W

Initializes the Caption. Args: sentence: List of word ids in the caption. state: Model state after generating the previous word.

Initializes the generator. Args: model: Object encapsulating a trained image-to-text model. Must have methods feed_image() and infe

Initializes the vocabulary. Args: vocab_file: File containing the vocabulary, where the words are the first whitespace-separated to

Constructor of Microsoft COCO helper class for reading and visualizing annotations. :param annotation_file (str): location of annotat

singular instance

singular instance