diff --git a/src/mnist_loader.py b/src/mnist_loader.py
index d17498c..a06422c 100644
--- a/src/mnist_loader.py
+++ b/src/mnist_loader.py
@@ -10,7 +10,7 @@ function usually called by our neural network code.
 
 #### Libraries
 # Standard library
-import cPickle
+import pickle
 import gzip
 
 # Third-party libraries
@@ -40,7 +40,9 @@ def load_data():
     below.
     """
     f = gzip.open('../data/mnist.pkl.gz', 'rb')
-    training_data, validation_data, test_data = cPickle.load(f)
+    t = pickle._Unpickler(f)
+    t.encoding = 'latin1'
+    training_data, validation_data, test_data = t.load()
     f.close()
     return (training_data, validation_data, test_data)
 
@@ -68,11 +70,11 @@ def load_data_wrapper():
     tr_d, va_d, te_d = load_data()
     training_inputs = [np.reshape(x, (784, 1)) for x in tr_d[0]]
     training_results = [vectorized_result(y) for y in tr_d[1]]
-    training_data = zip(training_inputs, training_results)
+    training_data = list(zip(training_inputs, training_results))
     validation_inputs = [np.reshape(x, (784, 1)) for x in va_d[0]]
-    validation_data = zip(validation_inputs, va_d[1])
+    validation_data = list(zip(validation_inputs, va_d[1]))
     test_inputs = [np.reshape(x, (784, 1)) for x in te_d[0]]
-    test_data = zip(test_inputs, te_d[1])
+    test_data = list(zip(test_inputs, te_d[1]))
     return (training_data, validation_data, test_data)
 
 def vectorized_result(j):
diff --git a/src/network.py b/src/network.py
index f66c362..d37f685 100644
--- a/src/network.py
+++ b/src/network.py
@@ -53,18 +53,18 @@ class Network(object):
         tracking progress, but slows things down substantially."""
         if test_data: n_test = len(test_data)
         n = len(training_data)
-        for j in xrange(epochs):
+        for j in range(epochs):
             random.shuffle(training_data)
             mini_batches = [
                 training_data[k:k+mini_batch_size]
-                for k in xrange(0, n, mini_batch_size)]
+                for k in range(0, n, mini_batch_size)]
             for mini_batch in mini_batches:
                 self.update_mini_batch(mini_batch, eta)
             if test_data:
-                print "Epoch {0}: {1} / {2}".format(
-                    j, self.evaluate(test_data), n_test)
+                print("Epoch {0}: {1} / {2}".format(
+                    j, self.evaluate(test_data), n_test))
             else:
-                print "Epoch {0} complete".format(j)
+                print("Epoch {0} complete".format(j))
 
     def update_mini_batch(self, mini_batch, eta):
         """Update the network's weights and biases by applying
@@ -109,7 +109,7 @@ class Network(object):
         # second-last layer, and so on.  It's a renumbering of the
         # scheme in the book, used here to take advantage of the fact
         # that Python can use negative indices in lists.
-        for l in xrange(2, self.num_layers):
+        for l in range(2, self.num_layers):
             z = zs[-l]
             sp = sigmoid_prime(z)
             delta = np.dot(self.weights[-l+1].transpose(), delta) * sp