Args: seed - initial index, N - maximum index Return: A random index between [0, N] except for seed

Args: filepath (string): path to data file Data format - list of characters, list of images, (row, col, ch) numpy arr

Compute the nearest neighbor of the input queries. Arguments: x: A normalized matrix of queries of size (batch_size x ke

Generates a random batch for training or validation. Structures each element of the batch as an 'episode'. Each episode contains epis

Load and preprocess images from a directory and write them to a file. Args: directory: Directory of alphabet sub-directories. write_file: F

Calculate Average Memory Loss Function positive - positive cosine similarity negative - negative cosine similarity ma

Crawls data directory and returns stuff.

Flatten matrix into a vector

Download Omniglot repo if it does not exist.

Download and prepare raw Omniglot data. Downloads the data from GitHub if it does not exist. Then load the images, augment with rotations if desi

Resize images to new dimensions.

Args: [test_image, same] = idx test_image = (test_category, test_category_image) same (bool) = if support image comes from t

Args: filepath (string): path to data file Data format - list of characters, list of images, (row, col, ch) numpy arr

Args: classes - number of classes in dataset rnd - number of iterations batch_size - size of batch