Keep partial end batch

code/DBN.py

@@ -158,6 +158,7 @@ def pretraining_functions(self, train_set_x, batch_size, k):
 
         # number of batches
         n_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
+        n_batches = int(numpy.ceil(n_batches / float(batch_size)))
         # begining of a batch, given `index`
         batch_begin = index * batch_size
         # ending of a batch given `index`
@@ -211,9 +212,9 @@ def build_finetune_functions(self, datasets, batch_size, learning_rate):
 
         # compute number of minibatches for training, validation and testing
         n_valid_batches = valid_set_x.get_value(borrow=True).shape[0]
-        n_valid_batches /= batch_size
         n_test_batches = test_set_x.get_value(borrow=True).shape[0]
-        n_test_batches /= batch_size
+        n_valid_batches = int(numpy.ceil(n_valid_batches / float(batch_size)))
+        n_test_batches = int(numpy.ceil(n_test_batches / float(batch_size)))
 
         index = T.lscalar('index')  # index to a [mini]batch
 

code/SdA.py

@@ -254,9 +254,9 @@ def build_finetune_functions(self, datasets, batch_size, learning_rate):
 
         # compute number of minibatches for training, validation and testing
         n_valid_batches = valid_set_x.get_value(borrow=True).shape[0]
-        n_valid_batches /= batch_size
         n_test_batches = test_set_x.get_value(borrow=True).shape[0]
-        n_test_batches /= batch_size
+        n_valid_batches = int(numpy.ceil(n_valid_batches / float(batch_size)))
+        n_test_batches = int(numpy.ceil(n_test_batches / float(batch_size)))
 
         index = T.lscalar('index')  # index to a [mini]batch
 
@@ -357,7 +357,7 @@ def test_SdA(finetune_lr=0.1, pretraining_epochs=15,
 
     # compute number of minibatches for training, validation and testing
     n_train_batches = train_set_x.get_value(borrow=True).shape[0]
-    n_train_batches /= batch_size
+    n_train_batches = int(numpy.ceil(n_train_batches / float(batch_size)))
 
     # numpy random generator
     # start-snippet-3

code/cA.py

@@ -246,7 +246,8 @@ def test_cA(learning_rate=0.01, training_epochs=20,
     train_set_x, train_set_y = datasets[0]
 
     # compute number of minibatches for training, validation and testing
-    n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
+    n_train_batches = train_set_x.get_value(borrow=True).shape[0]
+    n_train_batches = int(numpy.ceil(n_train_batches / float(batch_size)))
 
     # allocate symbolic variables for the data
     index = T.lscalar()    # index to a [mini]batch

code/convolutional_mlp.py

@@ -142,9 +142,9 @@ def evaluate_lenet5(learning_rate=0.1, n_epochs=200,
     n_train_batches = train_set_x.get_value(borrow=True).shape[0]
     n_valid_batches = valid_set_x.get_value(borrow=True).shape[0]
     n_test_batches = test_set_x.get_value(borrow=True).shape[0]
-    n_train_batches /= batch_size
-    n_valid_batches /= batch_size
-    n_test_batches /= batch_size
+    n_train_batches = int(numpy.ceil(n_train_batches / float(batch_size)))
+    n_valid_batches = int(numpy.ceil(n_valid_batches / float(batch_size)))
+    n_test_batches = int(numpy.ceil(n_test_batches / float(batch_size)))
 
     # allocate symbolic variables for the data
     index = T.lscalar()  # index to a [mini]batch

code/dA.py

@@ -280,7 +280,8 @@ def test_dA(learning_rate=0.1, training_epochs=15,
     train_set_x, train_set_y = datasets[0]
 
     # compute number of minibatches for training, validation and testing
-    n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
+    n_train_batches = train_set_x.get_value(borrow=True).shape[0]
+    n_train_batches = int(numpy.ceil(n_train_batches / float(batch_size)))
 
     # start-snippet-2
     # allocate symbolic variables for the data

code/logistic_cg.py

@@ -162,9 +162,12 @@ def cg_optimization_mnist(n_epochs=50, mnist_pkl_gz='mnist.pkl.gz'):
 
     batch_size = 600    # size of the minibatch
 
-    n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
-    n_valid_batches = valid_set_x.get_value(borrow=True).shape[0] / batch_size
-    n_test_batches = test_set_x.get_value(borrow=True).shape[0] / batch_size
+    n_train_batches = train_set_x.get_value(borrow=True).shape[0]
+    n_valid_batches = valid_set_x.get_value(borrow=True).shape[0]
+    n_test_batches = test_set_x.get_value(borrow=True).shape[0]
+    n_train_batches = int(numpy.ceil(n_train_batches / float(batch_size)))
+    n_valid_batches = int(numpy.ceil(n_valid_batches / float(batch_size)))
+    n_test_batches = int(numpy.ceil(n_test_batches / float(batch_size)))
 
     n_in = 28 * 28  # number of input units
     n_out = 10  # number of output units

code/logistic_sgd.py

@@ -273,9 +273,12 @@ def sgd_optimization_mnist(learning_rate=0.13, n_epochs=1000,
     test_set_x, test_set_y = datasets[2]
 
     # compute number of minibatches for training, validation and testing
-    n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
-    n_valid_batches = valid_set_x.get_value(borrow=True).shape[0] / batch_size
-    n_test_batches = test_set_x.get_value(borrow=True).shape[0] / batch_size
+    n_train_batches = train_set_x.get_value(borrow=True).shape[0]
+    n_valid_batches = valid_set_x.get_value(borrow=True).shape[0]
+    n_test_batches = test_set_x.get_value(borrow=True).shape[0]
+    n_train_batches = int(numpy.ceil(n_train_batches / float(batch_size)))
+    n_valid_batches = int(numpy.ceil(n_valid_batches / float(batch_size)))
+    n_test_batches = int(numpy.ceil(n_test_batches / float(batch_size)))
 
     ######################
     # BUILD ACTUAL MODEL #

code/mlp.py

@@ -228,9 +228,12 @@ def test_mlp(learning_rate=0.01, L1_reg=0.00, L2_reg=0.0001, n_epochs=1000,
     test_set_x, test_set_y = datasets[2]
 
     # compute number of minibatches for training, validation and testing
-    n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
-    n_valid_batches = valid_set_x.get_value(borrow=True).shape[0] / batch_size
-    n_test_batches = test_set_x.get_value(borrow=True).shape[0] / batch_size
+    n_train_batches = train_set_x.get_value(borrow=True).shape[0]
+    n_valid_batches = valid_set_x.get_value(borrow=True).shape[0]
+    n_test_batches = test_set_x.get_value(borrow=True).shape[0]
+    n_train_batches = int(numpy.ceil(n_train_batches / float(batch_size)))
+    n_valid_batches = int(numpy.ceil(n_valid_batches / float(batch_size)))
+    n_test_batches = int(numpy.ceil(n_test_batches / float(batch_size)))
 
     ######################
     # BUILD ACTUAL MODEL #

code/rbm.py

@@ -384,7 +384,8 @@ def test_rbm(learning_rate=0.1, training_epochs=15,
     test_set_x, test_set_y = datasets[2]
 
     # compute number of minibatches for training, validation and testing
-    n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
+    n_train_batches = train_set_x.get_value(borrow=True).shape[0]
+    n_train_batches = int(numpy.ceil(n_train_batches / float(batch_size)))
 
     # allocate symbolic variables for the data
     index = T.lscalar()    # index to a [mini]batch