Processes and saves a subset of images as TFRecord files in one thread. Args: thread_index: Integer thread identifier within [0, len(ranges)

Batches input images and captions. This function splits the caption into an input sequence and a target sequence, where the target sequence is th

Builds the inference graph from serialized GraphDef and SaverDef protos. Args: graph_def_file: File containing a serialized GraphDef proto.

Computes Rouge-L score given a set of reference and candidate sentences for the dataset Invoked by evaluate_captions.py :par

Main function to compute CIDEr score :param hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / ca

copy the refs.

Function maps counts of ngram to vector of tfidf weights. The function returns vec, an array of dictionary that store mapping

Convenient function for deleting a word.

Change the module's `cut` and `cut_for_search` functions to the parallel version. Note that this only works using dt, custom Tokenizer

Encode binary mask M using run-length encoding. :param M (bool 2D array) : binary mask to encode :return: R (object RLE)

Extract keywords from sentence using TF-IDF algorithm. Parameter: - topK: return how many top keywords. `None` for all po

filtering parameters. default skips that filter. :param catNms (str array) : get cats for given cat names :param supNms (str

Builds an Inception V3 subgraph for image embeddings. Args: images: A float32 Tensor of shape [batch, height, width, channels]. trainable:

Load cats with the specified ids. :param ids (int array) : integer ids specifying cats :return: cats (object array) : l

Load anns with the specified ids. :param ids (int array) : integer ids specifying img :return: imgs (object array) : lo

Parses a tensorflow.SequenceExample into an image and caption. Args: serialized: A scalar string Tensor; a single serialized SequenceExample.

Prefetches string values from disk into an input queue. In training the capacity of the queue is important because a larger queue means better mi

Decode an image, resize and apply random distortions. In training, images are distorted slightly differently depending on thread_id. Args: e

replace test(s) with new test(s), and returns the new score.

Convert polygon segmentation to binary mask. :param S (float array) : polygon segmentation mask :param h (int)

Compute the cosine similarity of two vectors. :param vec_hyp: array of dictionary for vector corresponding to hypothesis

test for key error

test for less data

test for more data

test for null data

test for right data

test for wrong_name

Extract keywords from sentence using TextRank algorithm. Parameter: - topK: return how many top keywords. `None` for all

Returns the integer word id of a word string.