diff --git a/check_mkl.py b/check_mkl.py
index b89c798..87d34f0 100644
--- a/check_mkl.py
+++ b/check_mkl.py
@@ -1,22 +1,15 @@
-
 # coding: utf-8
 
-# In[5]:
-
-
 from __future__ import division, print_function, absolute_import
 
 import tensorflow as tf
+
 from tensorflow.python.client import timeline
 
 # Import MNIST data
 from tensorflow.examples.tutorials.mnist import input_data
 mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
 
-
-# In[2]:
-
-
 # Training Parameters
 learning_rate = 0.001
 num_steps = 500
@@ -24,20 +17,18 @@
 display_step = 10
 
 # Network Parameters
-num_input = 784 # MNIST data input (img shape: 28*28)
-num_classes = 10 # MNIST total classes (0-9 digits)
-dropout = 0.75 # Dropout, probability to keep units
+num_input = 784  # MNIST data input (img shape: 28*28)
+num_classes = 10  # MNIST total classes (0-9 digits)
+dropout = 0.75  # Dropout, probability to keep units
 
 # tf Graph input
 X = tf.placeholder(tf.float32, [None, num_input])
 Y = tf.placeholder(tf.float32, [None, num_classes])
-keep_prob = tf.placeholder(tf.float32) # dropout (keep probability)
-
+keep_prob = tf.placeholder(tf.float32)  # dropout (keep probability)
 
-# In[3]:
+# Create some wrappers for simplicity
 
 
-# Create some wrappers for simplicity
 def conv2d(x, W, b, strides=1):
     # Conv2D wrapper, with bias and relu activation
     x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')
@@ -50,8 +41,9 @@ def maxpool2d(x, k=2):
     return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],
                           padding='SAME')
 
-
 # Create model
+
+
 def conv_net(x, weights, biases, dropout):
     # MNIST data input is a 1-D vector of 784 features (28*28 pixels)
     # Reshape to match picture format [Height x Width x Channel]
@@ -80,10 +72,6 @@ def conv_net(x, weights, biases, dropout):
     out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
     return out
 
-
-# In[4]:
-
-
 # Store layers weight & bias
 weights = {
     # 5x5 conv, 1 input, 32 outputs
@@ -91,7 +79,7 @@ def conv_net(x, weights, biases, dropout):
     # 5x5 conv, 32 inputs, 64 outputs
     'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),
     # fully connected, 7*7*64 inputs, 1024 outputs
-    'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])),
+    'wd1': tf.Variable(tf.random_normal([7 * 7 * 64, 1024])),
     # 1024 inputs, 10 outputs (class prediction)
     'out': tf.Variable(tf.random_normal([1024, num_classes]))
 }
@@ -113,7 +101,6 @@ def conv_net(x, weights, biases, dropout):
 optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
 train_op = optimizer.minimize(loss_op)
 
-
 # Evaluate model
 correct_pred = tf.equal(tf.argmax(prediction, 1), tf.argmax(Y, 1))
 accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
@@ -121,10 +108,6 @@ def conv_net(x, weights, biases, dropout):
 # Initialize the variables (i.e. assign their default value)
 init = tf.global_variables_initializer()
 
-
-# In[6]:
-
-
 # Start training
 with tf.Session() as sess:
     run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
@@ -133,19 +116,10 @@ def conv_net(x, weights, biases, dropout):
     # Run the initializer
     sess.run(init)
 
-    for step in range(1, num_steps+1):
-        batch_x, batch_y = mnist.train.next_batch(batch_size)
-        # Run optimization op (backprop)
-        sess.run(train_op, feed_dict={X: batch_x, Y: batch_y, keep_prob: dropout})
-        if step % display_step == 0 or step == 1:
-            # Calculate batch loss and accuracy
-            loss, acc = sess.run([loss_op, accuracy],
-                                 feed_dict={X: batch_x, Y: batch_y, keep_prob: 1.0},
-                                 options=run_options,
-                                 run_metadata=run_metadata)
-        tl = timeline.Timeline(run_metadata.step_stats)
-        ctf = tl.generate_chrome_trace_format()
-        with open('timeline.json', 'w') as f:
-            f.write(ctf)
-        break
-
+    batch_x, batch_y = mnist.train.next_batch(batch_size)
+    # Run optimization op (backprop)
+    sess.run(train_op, feed_dict={X: batch_x, Y: batch_y, keep_prob: dropout})
+    tl = timeline.Timeline(run_metadata.step_stats)
+    ctf = tl.generate_chrome_trace_format()
+    with open('timeline.json', 'w') as f:
+        f.write(ctf)