Mercurial > ift6266

view datasets/defs.py @ 175:224321bf043a

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Define the ocr dataset and use the existing split for nist.
author Arnaud Bergeron <abergeron@gmail.com>
date Sat, 27 Feb 2010 13:56:14 -0500
parents datasets/nist.py@e3de934a98b6
children 76bc047df5ee
line wrap: on
line source

__all__ = ['nist_digits', 'nist_lower', 'nist_upper', 'nist_all']

from ftfile import FTDataSet

NIST_PATH = '/data/lisa/data/nist/by_class/'
DATA_PATH = '/data/lisa/data/ift6266h10/'

nist_digits = FTDataSet(train_data = [NIST_PATH+'digits/digits_train_data.ft'],
                        train_lbl = [NIST_PATH+'digits/digits_train_labels.ft'],
                        test_data = [NIST_PATH+'digits/digits_test_data.ft'],
                        test_lbl = [NIST_PATH+'digits/digits_test_labels.ft'])
nist_lower = FTDataSet(train_data = [NIST_PATH+'lower/lower_train_data.ft'],
                        train_lbl = [NIST_PATH+'lower/lower_train_labels.ft'],
                        test_data = [NIST_PATH+'lower/lower_test_data.ft'],
                        test_lbl = [NIST_PATH+'lower/lower_test_labels.ft'])
nist_upper = FTDataSet(train_data = [NIST_PATH+'upper/upper_train_data.ft'],
                        train_lbl = [NIST_PATH+'upper/upper_train_labels.ft'],
                        test_data = [NIST_PATH+'upper/upper_test_data.ft'],
                        test_lbl = [NIST_PATH+'upper/upper_test_labels.ft'])



nist_all = FTDataSet(train_data = [DATA_PATH+'train_data.ft'],
                     train_lbl = [DATA_PATH+'train_labels.ft'],
                     test_data = [DATA_PATH+'test_data.ft'],
                     test_lbl = [DATA_PATH+'test_labels.ft'],
                     valid_data = [DATA_PATH+'valid_data.ft'],
                     valid_lbl = [DATA_PATH+'valid_labels.ft'])

ocr = FTDataSet(train_data = [DATA_PATH+'ocr_train_data.ft'],
                train_lbl = [DATA_PATH+'ocr_train_labels.ft'],
                test_data = [DATA_PATH+'ocr_test_data.ft'],
                test_lbl = [DATA_PATH+'ocr_test_labels.ft'],
                valid_data = [DATA_PATH+'ocr_valid_data.ft'],
                valid_lbl = [DATA_PATH+'ocr_valid_labels.ft'])