loaders.load_MNIST_with_embeddings

pai4sk.simsearch.loaders.load_MNIST_with_embeddings(image_file_path, label_file_path, norm='l1', use_sparse=True)

Loads MNIST dataset into arrays W, X, labels, ids

Parameters

• image_file_path (string) – file path location for the MNIST images

• label_file_path (string) – file path location for the MNIST labels

• norm (string (default='l1')) – l2 if the user wants to normalize the data using l2 normalization

• use_sparse (bool (default='True')) – False if the user wants to load MNIST in non-sparse format

Returns

• W (array_like, shape (n_features, n_dimensions)) – Embedding vectors

• X (array_like, sparse_matrix, shape (n_samples, n_features)) – Feature vectors

• labels (array-like, shape (n_samples,)) – labels are the class labels of the samples in X

• ids (array_like, shape (n_samples,)) – ids are the ids of the samples in X