Mercurial > ift6266

annotate datasets/defs.py @ 178:938bd350dbf0

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Make the datasets iterators return theano shared slices with the appropriate types.
author Arnaud Bergeron <abergeron@gmail.com>
date Sat, 27 Feb 2010 15:09:02 -0500
parents 224321bf043a
children 76bc047df5ee
rev   line source
164
e3de934a98b6 Add nist_lower, nist_upper, nist_all
Arnaud Bergeron <abergeron@gmail.com>
parents: 163
diff changeset
1 __all__ = ['nist_digits', 'nist_lower', 'nist_upper', 'nist_all']
163
4b28d7382dbf Add inital implementation of datasets.
Arnaud Bergeron <abergeron@gmail.com>
parents:
diff changeset
2
4b28d7382dbf Add inital implementation of datasets.
Arnaud Bergeron <abergeron@gmail.com>
parents:
diff changeset
3 from ftfile import FTDataSet
4b28d7382dbf Add inital implementation of datasets.
Arnaud Bergeron <abergeron@gmail.com>
parents:
diff changeset
4
175
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
5 NIST_PATH = '/data/lisa/data/nist/by_class/'
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
6 DATA_PATH = '/data/lisa/data/ift6266h10/'
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
7
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
8 nist_digits = FTDataSet(train_data = [NIST_PATH+'digits/digits_train_data.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
9 train_lbl = [NIST_PATH+'digits/digits_train_labels.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
10 test_data = [NIST_PATH+'digits/digits_test_data.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
11 test_lbl = [NIST_PATH+'digits/digits_test_labels.ft'])
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
12 nist_lower = FTDataSet(train_data = [NIST_PATH+'lower/lower_train_data.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
13 train_lbl = [NIST_PATH+'lower/lower_train_labels.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
14 test_data = [NIST_PATH+'lower/lower_test_data.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
15 test_lbl = [NIST_PATH+'lower/lower_test_labels.ft'])
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
16 nist_upper = FTDataSet(train_data = [NIST_PATH+'upper/upper_train_data.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
17 train_lbl = [NIST_PATH+'upper/upper_train_labels.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
18 test_data = [NIST_PATH+'upper/upper_test_data.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
19 test_lbl = [NIST_PATH+'upper/upper_test_labels.ft'])
163
4b28d7382dbf Add inital implementation of datasets.
Arnaud Bergeron <abergeron@gmail.com>
parents:
diff changeset
20
175
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
21
163
4b28d7382dbf Add inital implementation of datasets.
Arnaud Bergeron <abergeron@gmail.com>
parents:
diff changeset
22
175
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
23 nist_all = FTDataSet(train_data = [DATA_PATH+'train_data.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
24 train_lbl = [DATA_PATH+'train_labels.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
25 test_data = [DATA_PATH+'test_data.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
26 test_lbl = [DATA_PATH+'test_labels.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
27 valid_data = [DATA_PATH+'valid_data.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
28 valid_lbl = [DATA_PATH+'valid_labels.ft'])
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
29
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
30 ocr = FTDataSet(train_data = [DATA_PATH+'ocr_train_data.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
31 train_lbl = [DATA_PATH+'ocr_train_labels.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
32 test_data = [DATA_PATH+'ocr_test_data.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
33 test_lbl = [DATA_PATH+'ocr_test_labels.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
34 valid_data = [DATA_PATH+'ocr_valid_data.ft'],
224321bf043a Define the ocr dataset and use the existing split for nist.
Arnaud Bergeron <abergeron@gmail.com>
parents: 164
diff changeset
35 valid_lbl = [DATA_PATH+'ocr_valid_labels.ft'])