Analyzes the output of the Inception graph to retrieve the highest scores and their positions in the tensor, which correspond to categories.

This is a testing function that returns whether the top label index is the one that's expected.

Reads a model graph definition from disk, and creates a session object you can use to run it.

Given the output of a model run, and the name of a file containing the labels this prints out the top five highest-scoring values.

Takes a file name, and loads a list of labels from it, one per line, and returns a vector of the strings. It pads with empty strings so the length of

Given an image file name, read in the data, try to decode it as an image, resize it to the requested size, and then scale the values as desired.

Builds a very simple CNN outputing num_categories. Args: img_shape (int): The shape of the image to feed the CNN - defaults

Converts an HD5F file to a .pb file for use with Tensorflow. Args: modelPath (str): path to the .h5 file outdir (str): pa

Inverts the key/value pairs of the supplied dictionary. Args: someDictionary (dict): The dictionary for which you would like the

Trains the supplied model agaist train and test locations specified in the args. During the training, each epoch will be evaluated for v