Fix format and some typos

examples/1_Introduction/helloworld.py

@@ -9,7 +9,7 @@
 
 import tensorflow as tf
 
-#Simple hello world using TensorFlow
+# Simple hello world using TensorFlow
 
 # Create a Constant op
 # The op is added as a node to the default graph.

examples/2_BasicModels/linear_regression.py

@@ -52,7 +52,7 @@
         for (x, y) in zip(train_X, train_Y):
             sess.run(optimizer, feed_dict={X: x, Y: y})
 
-        #Display logs per epoch step
+        # Display logs per epoch step
         if (epoch+1) % display_step == 0:
             c = sess.run(cost, feed_dict={X: train_X, Y:train_Y})
             print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(c), \
@@ -62,7 +62,7 @@
     training_cost = sess.run(cost, feed_dict={X: train_X, Y: train_Y})
     print("Training cost=", training_cost, "W=", sess.run(W), "b=", sess.run(b), '\n')
 
-    #Graphic display
+    # Graphic display
     plt.plot(train_X, train_Y, 'ro', label='Original data')
     plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label='Fitted line')
     plt.legend()

examples/2_BasicModels/logistic_regression.py

@@ -11,7 +11,7 @@
 
 import tensorflow as tf
 
-# Import MINST data
+# Import MNIST data
 from tensorflow.examples.tutorials.mnist import input_data
 mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
 

examples/2_BasicModels/nearest_neighbor.py

@@ -12,7 +12,7 @@
 import numpy as np
 import tensorflow as tf
 
-# Import MINST data
+# Import MNIST data
 from tensorflow.examples.tutorials.mnist import input_data
 mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
 

examples/3_NeuralNetworks/autoencoder.py

@@ -15,7 +15,7 @@
 import numpy as np
 import matplotlib.pyplot as plt
 
-# Import MINST data
+# Import MNIST data
 from tensorflow.examples.tutorials.mnist import input_data
 mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
 

examples/3_NeuralNetworks/bidirectional_rnn.py

@@ -1,5 +1,5 @@
 '''
-A Bidirectional Reccurent Neural Network (LSTM) implementation example using TensorFlow library.
+A Bidirectional Recurrent Neural Network (LSTM) implementation example using TensorFlow library.
 This example is using the MNIST database of handwritten digits (http://yann.lecun.com/exdb/mnist/)
 Long Short Term Memory paper: http://deeplearning.cs.cmu.edu/pdfs/Hochreiter97_lstm.pdf
 
@@ -13,12 +13,12 @@
 from tensorflow.python.ops import rnn, rnn_cell
 import numpy as np
 
-# Import MINST data
+# Import MNIST data
 from tensorflow.examples.tutorials.mnist import input_data
 mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
 
 '''
-To classify images using a bidirectional reccurent neural network, we consider
+To classify images using a bidirectional recurrent neural network, we consider
 every image row as a sequence of pixels. Because MNIST image shape is 28*28px,
 we will then handle 28 sequences of 28 steps for every sample.
 '''
@@ -41,7 +41,7 @@
 
 # Define weights
 weights = {
-    # Hidden layer weights => 2*n_hidden because of foward + backward cells
+    # Hidden layer weights => 2*n_hidden because of forward + backward cells
     'out': tf.Variable(tf.random_normal([2*n_hidden, n_classes]))
 }
 biases = {

examples/3_NeuralNetworks/convolutional_network.py

@@ -11,7 +11,7 @@
 
 import tensorflow as tf
 
-# Import MINST data
+# Import MNIST data
 from tensorflow.examples.tutorials.mnist import input_data
 mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
 

examples/3_NeuralNetworks/dynamic_rnn.py

@@ -1,5 +1,5 @@
 '''
-A Dynamic Reccurent Neural Network (LSTM) implementation example using
+A Dynamic Recurrent Neural Network (LSTM) implementation example using
 TensorFlow library. This example is using a toy dataset to classify linear
 sequences. The generated sequences have variable length.
 
@@ -26,7 +26,7 @@ class ToySequenceData(object):
 
     NOTICE:
     We have to pad each sequence to reach 'max_seq_len' for TensorFlow
-    consistency (we cannot feed a numpy array with unconsistent
+    consistency (we cannot feed a numpy array with inconsistent
     dimensions). The dynamic calculation will then be perform thanks to
     'seqlen' attribute that records every actual sequence length.
     """
@@ -130,7 +130,7 @@ def dynamicRNN(x, seqlen, weights, biases):
                                 sequence_length=seqlen)
 
     # When performing dynamic calculation, we must retrieve the last
-    # dynamically computed output, i.e, if a sequence length is 10, we need
+    # dynamically computed output, i.e., if a sequence length is 10, we need
     # to retrieve the 10th output.
     # However TensorFlow doesn't support advanced indexing yet, so we build
     # a custom op that for each sample in batch size, get its length and

examples/3_NeuralNetworks/multilayer_perceptron.py

@@ -9,7 +9,7 @@
 
 from __future__ import print_function
 
-# Import MINST data
+# Import MNIST data
 from tensorflow.examples.tutorials.mnist import input_data
 mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
 

examples/3_NeuralNetworks/recurrent_network.py

@@ -1,5 +1,5 @@
 '''
-A Reccurent Neural Network (LSTM) implementation example using TensorFlow library.
+A Recurrent Neural Network (LSTM) implementation example using TensorFlow library.
 This example is using the MNIST database of handwritten digits (http://yann.lecun.com/exdb/mnist/)
 Long Short Term Memory paper: http://deeplearning.cs.cmu.edu/pdfs/Hochreiter97_lstm.pdf
 
@@ -18,7 +18,7 @@
 mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
 
 '''
-To classify images using a reccurent neural network, we consider every image
+To classify images using a recurrent neural network, we consider every image
 row as a sequence of pixels. Because MNIST image shape is 28*28px, we will then
 handle 28 sequences of 28 steps for every sample.
 '''

examples/4_Utils/save_restore_model.py

@@ -9,7 +9,7 @@
 
 from __future__ import print_function
 
-# Import MINST data
+# Import MNIST data
 from tensorflow.examples.tutorials.mnist import input_data
 mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
 

examples/4_Utils/tensorboard_advanced.py

@@ -11,7 +11,7 @@
 
 import tensorflow as tf
 
-# Import MINST data
+# Import MNIST data
 from tensorflow.examples.tutorials.mnist import input_data
 mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
 
@@ -64,7 +64,7 @@ def multilayer_perceptron(x, weights, biases):
 }
 
 # Encapsulating all ops into scopes, making Tensorboard's Graph
-# visualization more convenient
+# Visualization more convenient
 with tf.name_scope('Model'):
     # Build model
     pred = multilayer_perceptron(x, weights, biases)

examples/4_Utils/tensorboard_basic.py

@@ -11,7 +11,7 @@
 
 import tensorflow as tf
 
-# Import MINST data
+# Import MNIST data
 from tensorflow.examples.tutorials.mnist import input_data
 mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
 

examples/5_MultiGPU/multigpu_basics.py

@@ -18,10 +18,10 @@
 import tensorflow as tf
 import datetime
 
-#Processing Units logs
+# Processing Units logs
 log_device_placement = True
 
-#num of multiplications to perform
+# Num of multiplications to perform
 n = 10
 
 '''
@@ -30,11 +30,11 @@
  * Single GPU computation time: 0:00:11.277449
  * Multi GPU computation time: 0:00:07.131701
 '''
-#Create random large matrix
+# Create random large matrix
 A = np.random.rand(1e4, 1e4).astype('float32')
 B = np.random.rand(1e4, 1e4).astype('float32')
 
-# Creates a graph to store results
+# Create a graph to store results
 c1 = []
 c2 = []
 
@@ -50,7 +50,7 @@ def matpow(M, n):
 with tf.device('/gpu:0'):
     a = tf.constant(A)
     b = tf.constant(B)
-    #compute A^n and B^n and store results in c1
+    # Compute A^n and B^n and store results in c1
     c1.append(matpow(a, n))
     c1.append(matpow(b, n))
 
@@ -59,23 +59,23 @@ def matpow(M, n):
 
 t1_1 = datetime.datetime.now()
 with tf.Session(config=tf.ConfigProto(log_device_placement=log_device_placement)) as sess:
-    # Runs the op.
+    # Run the op.
     sess.run(sum)
 t2_1 = datetime.datetime.now()
 
 
 '''
 Multi GPU computing
 '''
-#GPU:0 computes A^n
+# GPU:0 computes A^n
 with tf.device('/gpu:0'):
-    #compute A^n and store result in c2
+    # Compute A^n and store result in c2
     a = tf.constant(A)
     c2.append(matpow(a, n))
 
-#GPU:1 computes B^n
+# GPU:1 computes B^n
 with tf.device('/gpu:1'):
-    #compute B^n and store result in c2
+    # Compute B^n and store result in c2
     b = tf.constant(B)
     c2.append(matpow(b, n))
 
@@ -84,7 +84,7 @@ def matpow(M, n):
 
 t1_2 = datetime.datetime.now()
 with tf.Session(config=tf.ConfigProto(log_device_placement=log_device_placement)) as sess:
-    # Runs the op.
+    # Run the op.
     sess.run(sum)
 t2_2 = datetime.datetime.now()