Mercurial > ift6266

changeset 269:4533350d7361

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Ajout d'une fonctionnalite pour pouvoir definir un range de fichiers d'entrainement de P07 utilises. Utile pour pre-entrainer et fine-tuner avec des donnees differentes
author SylvainPL <sylvain.pannetier.lebeuf@umontreal.ca>
date Sat, 20 Mar 2010 10:19:11 -0400
parents b077d9e97a3b
children d41fe003fade
files datasets/defs.py
diffstat 1 files changed, 4 insertions(+), 2 deletions(-) [+]
line wrap: on
line diff
--- a/datasets/defs.py	Fri Mar 19 11:31:57 2010 -0400
+++ b/datasets/defs.py	Sat Mar 20 10:19:11 2010 -0400
@@ -43,8 +43,10 @@
                 valid_lbl = [os.path.join(DATA_PATH,'ocr_valid_labels.ft')],
                 indtype=theano.config.floatX, inscale=255., maxsize=maxsize)
 
-nist_P07 = lambda maxsize=None: FTDataSet(train_data = [os.path.join(DATA_PATH,'data/P07_train'+str(i)+'_data.ft') for i in range(100)],
-                     train_lbl = [os.path.join(DATA_PATH,'data/P07_train'+str(i)+'_labels.ft') for i in range(100)],
+#There is 2 more arguments here to can choose smaller datasets based on the file number.
+#This is usefull to get different data for pre-training and finetuning
+nist_P07 = lambda maxsize=None, min_file=0, max_file=100: FTDataSet(train_data = [os.path.join(DATA_PATH,'data/P07_train'+str(i)+'_data.ft') for i in range(min_file, max_file)],
+                     train_lbl = [os.path.join(DATA_PATH,'data/P07_train'+str(i)+'_labels.ft') for i in range(min_file, max_file)],
                      test_data = [os.path.join(DATA_PATH,'data/P07_test_data.ft')],
                      test_lbl = [os.path.join(DATA_PATH,'data/P07_test_labels.ft')],
                      valid_data = [os.path.join(DATA_PATH,'data/P07_valid_data.ft')],