diff --git a/network3.py b/network3.py
index ff8afa8..dc9133f 100644
--- a/network3.py
+++ b/network3.py
@@ -224,9 +224,9 @@ def __init__(self, filter_shape, image_shape, poolsize=(2, 2),
 
     def set_inpt(self, inpt, inpt_dropout, mini_batch_size):
         self.inpt = inpt.reshape(self.image_shape)
-        conv_out = conv.conv2d(
+        conv_out = theano.tensor.nnet.conv2d(
             input=self.inpt, filters=self.w, filter_shape=self.filter_shape,
-            image_shape=self.image_shape)
+            input_shape=self.image_shape)
         pooled_out = pool_2d(
             input=conv_out, ws=self.poolsize, ignore_border=True)
         self.output = self.activation_fn(
diff --git a/test.py b/test.py
index d1f4996..ea4864f 100644
--- a/test.py
+++ b/test.py
@@ -15,16 +15,28 @@
         dobrzanski.michal.daniel@gmail.com
 """
 
+from PIL import Image
+
+
+def show_img(char_np_array):
+    char_np_array = char_np_array.reshape(28, 28)
+    char_img = Image.fromarray((char_np_array * 255))
+    char_img.show()
+
+
 # ----------------------
 # - read the input data:
-'''
 import mnist_loader
+
 training_data, validation_data, test_data = mnist_loader.load_data_wrapper()
 training_data = list(training_data)
-'''
+
+show_img(training_data[0][0])
+
+
 # ---------------------
 # - network.py example:
-#import network
+# import network
 
 '''
 net = network.Network([784, 30, 10])
@@ -33,7 +45,7 @@
 
 # ----------------------
 # - network2.py example:
-#import network2
+# import network2
 
 '''
 net = network2.Network([784, 30, 10], cost=network2.CrossEntropyCost)
@@ -86,7 +98,6 @@
     monitor_evaluation_accuracy=True)
 '''
 
-
 # ----------------------
 # Theano and CUDA
 # ----------------------
@@ -124,18 +135,19 @@
 
 
 """
+
+
 def testTheano():
-    from theano import function, config, shared, sandbox
-    import theano.tensor as T
+    from theano import function, config, shared, tensor
     import numpy
     import time
-    print("Testing Theano library...")
+
     vlen = 10 * 30 * 768  # 10 x #cores x # threads per core
     iters = 1000
 
     rng = numpy.random.RandomState(22)
     x = shared(numpy.asarray(rng.rand(vlen), config.floatX))
-    f = function([], T.exp(x))
+    f = function([], tensor.exp(x))
     print(f.maker.fgraph.toposort())
     t0 = time.time()
     for i in range(iters):
@@ -143,23 +155,29 @@ def testTheano():
     t1 = time.time()
     print("Looping %d times took %f seconds" % (iters, t1 - t0))
     print("Result is %s" % (r,))
-    if numpy.any([isinstance(x.op, T.Elemwise) for x in f.maker.fgraph.toposort()]):
+    if numpy.any([isinstance(x.op, tensor.Elemwise) and
+                  ('Gpu' not in type(x.op).__name__)
+                  for x in f.maker.fgraph.toposort()]):
         print('Used the cpu')
     else:
         print('Used the gpu')
-# Perform check:
-#testTheano()
 
 
+# Perform check:
+testTheano()
+
 # ----------------------
 # - network3.py example:
 import network3
-from network3 import Network, ConvPoolLayer, FullyConnectedLayer, SoftmaxLayer # softmax plus log-likelihood cost is more common in modern image classification networks.
+from network3 import Network, ConvPoolLayer, FullyConnectedLayer, \
+    SoftmaxLayer  # softmax plus log-likelihood cost is more common in modern image classification networks.
 
 # read data:
+'''
 training_data, validation_data, test_data = network3.load_data_shared()
 # mini-batch size:
 mini_batch_size = 10
+'''
 
 # chapter 6 - shallow architecture using just a single hidden layer, containing 100 hidden neurons.
 '''
@@ -195,6 +213,7 @@ def testTheano():
 '''
 
 # chapter 6 -  rectified linear units and some l2 regularization (lmbda=0.1) => even better accuracy
+'''
 from network3 import ReLU
 net = Network([
     ConvPoolLayer(image_shape=(mini_batch_size, 1, 28, 28),
@@ -208,3 +227,4 @@ def testTheano():
     FullyConnectedLayer(n_in=40*4*4, n_out=100, activation_fn=ReLU),
     SoftmaxLayer(n_in=100, n_out=10)], mini_batch_size)
 net.SGD(training_data, 60, mini_batch_size, 0.03, validation_data, test_data, lmbda=0.1)
+'''