added in some really basic comments

Author: nlintz

0_multiply.py

@@ -1,11 +1,11 @@
 import tensorflow as tf
 
-a = tf.placeholder("float")
-b = tf.placeholder("float")
+a = tf.placeholder("float") # Create a symbolic variable 'a'
+b = tf.placeholder("float") # Create a symbolic variable 'b'
 
-y = tf.mul(a, b)
+y = tf.mul(a, b) # multiply the symbolic variables
 
-sess = tf.Session()
+sess = tf.Session() # create a session to evaluate the symbolic expressions
 
-print "%f should equal 2.0" % sess.run(y, feed_dict={a: 1, b: 2})
+print "%f should equal 2.0" % sess.run(y, feed_dict={a: 1, b: 2}) # eval expressions with parameters for a and b
 print "%f should equal 9.0" % sess.run(y, feed_dict={a: 3, b: 3})

1_linear_regression.py

@@ -2,29 +2,29 @@
 import numpy as np
 
 trX = np.linspace(-1, 1, 101)
-trY = 2 * trX + np.random.randn(*trX.shape) * 0.33
+trY = 2 * trX + np.random.randn(*trX.shape) * 0.33 # create a y value which is approximately linear but with some random noise
 
-X = tf.placeholder("float")
+X = tf.placeholder("float") # create symbolic variables
 Y = tf.placeholder("float")
 
 
 def model(X, w):
-    return tf.mul(X, w)
+    return tf.mul(X, w) # lr is just X*w so this model line is pretty simple
 
 
-w = tf.Variable(0.0, name="weights")
+w = tf.Variable(0.0, name="weights") # create a shared variable (like theano.shared) for the weight matrix
 y_model = model(X, w)
 
-cost = (tf.pow(Y-y_model, 2))
+cost = (tf.pow(Y-y_model, 2)) # use sqr error for cost function
 
-train_op = tf.train.GradientDescentOptimizer(0.01).minimize(cost)
+train_op = tf.train.GradientDescentOptimizer(0.01).minimize(cost) # construct an optimizer to minimize cost and fit line to my data
 
 sess = tf.Session()
-init = tf.initialize_all_variables()
+init = tf.initialize_all_variables() # you need to initialize variables (in this case just variable W)
 sess.run(init)
 
 for i in range(100):
-    for (x, y) in zip(trX, trY):
+    for (x, y) in zip(trX, trY): 
         sess.run(train_op, feed_dict={X: x, Y: y})
 
 print(sess.run(w))  # something around 2

2_logistic_regression.py

@@ -8,22 +8,22 @@ def init_weights(shape):
 
 
 def model(X, w):
-    return tf.matmul(X, w)
+    return tf.matmul(X, w) # notice we use the same model as linear regression, this is because there is a baked in cost function which performs softmax and cross entropy
 
 
 mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
 trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels
 
-X = tf.placeholder("float", [None, 784])
+X = tf.placeholder("float", [None, 784]) # create symbolic variables
 Y = tf.placeholder("float", [None, 10])
 
-w = init_weights([784, 10])
+w = init_weights([784, 10]) # like in linear regression, we need a shared variable weight matrix for logistic regression
 
 py_x = model(X, w)
 
-cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(py_x, Y))
-train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost)
-predict_op = tf.argmax(py_x, 1)
+cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(py_x, Y)) # compute mean cross entropy (softmax is applied internally)
+train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost) # construct optimizer
+predict_op = tf.argmax(py_x, 1) # at predict time, evaluate the argmax of the logistic regression
 
 sess = tf.Session()
 init = tf.initialize_all_variables()

3_net.py

@@ -8,8 +8,8 @@ def init_weights(shape):
 
 
 def model(X, w_h, w_o):
-    h = tf.nn.sigmoid(tf.matmul(X, w_h))
-    return tf.matmul(h, w_o)
+    h = tf.nn.sigmoid(tf.matmul(X, w_h)) # this is a basic mlp, think 2 stacked logistic regressions
+    return tf.matmul(h, w_o) # note that we dont take the softmax at the end because our cost fn does that for us
 
 
 mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
@@ -18,13 +18,13 @@ def model(X, w_h, w_o):
 X = tf.placeholder("float", [None, 784])
 Y = tf.placeholder("float", [None, 10])
 
-w_h = init_weights([784, 625])
+w_h = init_weights([784, 625]) # create symbolic variables
 w_o = init_weights([625, 10])
 
 py_x = model(X, w_h, w_o)
 
-cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(py_x, Y))
-train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost)
+cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(py_x, Y)) # compute costs
+train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost) # construct an optimizer
 predict_op = tf.argmax(py_x, 1)
 
 sess = tf.Session()

4_modern_net.py

@@ -7,7 +7,7 @@ def init_weights(shape):
     return tf.Variable(tf.random_normal(shape, stddev=0.01))
 
 
-def model(X, w_h, w_h2, w_o, p_drop_input, p_drop_hidden):
+def model(X, w_h, w_h2, w_o, p_drop_input, p_drop_hidden): # this network is the same as the previous one except with an extra hidden layer + dropout
     X = tf.nn.dropout(X, p_drop_input)
     h = tf.nn.relu(tf.matmul(X, w_h))