code for lecture 2

Author: chiphuyen

2017/README.md

@@ -28,7 +28,4 @@ Embedding visualization with TensorBoard<br>
 Usage of summary ops<br>
 Exercises to be familiar with other special TensorFlow ops<br>
 Demonstration of the danger of lazy loading <br>
-Convolutional GRU (CRGU) (by Lukasz Kaiser)
-
-
-
+Convolutional GRU (CRGU) (by Lukasz Kaiser)

examples/02_lazy_loading.py

@@ -0,0 +1,43 @@
+""" Example of lazy vs normal loading
+Created by Chip Huyen (huyenn@stanford.edu)
+CS20: "TensorFlow for Deep Learning Research"
+cs20.stanford.edu
+Lecture 02
+"""
+import os
+os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
+
+import tensorflow as tf 
+
+######################################## 
+## NORMAL LOADING   			      ##
+## print out a graph with 1 Add node  ## 
+########################################
+
+x = tf.Variable(10, name='x')
+y = tf.Variable(20, name='y')
+z = tf.add(x, y)
+
+with tf.Session() as sess:
+	sess.run(tf.global_variables_initializer())
+	writer = tf.summary.FileWriter('graphs/normal_loading', sess.graph)
+	for _ in range(10):
+		sess.run(z)
+	print(tf.get_default_graph().as_graph_def())
+	writer.close()
+
+######################################## 
+## LAZY LOADING   					  ##
+## print out a graph with 10 Add nodes## 
+########################################
+
+x = tf.Variable(10, name='x')
+y = tf.Variable(20, name='y')
+
+with tf.Session() as sess:
+	sess.run(tf.global_variables_initializer())
+	writer = tf.summary.FileWriter('graphs/lazy_loading', sess.graph)
+	for _ in range(10):
+		sess.run(tf.add(x, y))
+	print(tf.get_default_graph().as_graph_def()) 
+	writer.close()

examples/02_placeholder.py

@@ -0,0 +1,35 @@
+""" Placeholder and feed_dict example
+Created by Chip Huyen (huyenn@stanford.edu)
+CS20: "TensorFlow for Deep Learning Research"
+cs20.stanford.edu
+Lecture 02
+"""
+import os
+os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
+
+import tensorflow as tf
+
+# Example 1: feed_dict with placeholder
+
+# a is a placeholderfor a vector of 3 elements, type tf.float32
+a = tf.placeholder(tf.float32, shape=[3])
+b = tf.constant([5, 5, 5], tf.float32)
+
+# use the placeholder as you would a constant
+c = a + b  # short for tf.add(a, b)
+
+writer = tf.summary.FileWriter('graphs/placeholders', tf.get_default_graph())
+with tf.Session() as sess:
+    # compute the value of c given the value of a is [1, 2, 3]
+    print(sess.run(c, {a: [1, 2, 3]}))                 # [6. 7. 8.]
+writer.close()
+
+
+# Example 2: feed_dict with variables
+a = tf.add(2, 5)
+b = tf.multiply(a, 3)
+
+with tf.Session() as sess:
+    print(sess.run(b))                                 # >> 21
+    # compute the value of b given the value of a is 15
+    print(sess.run(b, feed_dict={a: 15}))              # >> 45

examples/02_simple_tf.py

@@ -0,0 +1,62 @@
+""" Simple TensorFlow's ops
+Created by Chip Huyen (huyenn@stanford.edu)
+CS20: "TensorFlow for Deep Learning Research"
+cs20.stanford.edu
+"""
+import os
+os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
+
+import numpy as np
+import tensorflow as tf
+
+# Example 1: Simple ways to create log file writer
+a = tf.constant(2, name='a')
+b = tf.constant(3, name='b')
+x = tf.add(a, b, name='add')
+writer = tf.summary.FileWriter('./graphs/simple', tf.get_default_graph()) 
+with tf.Session() as sess:
+    # writer = tf.summary.FileWriter('./graphs', sess.graph) 
+    print(sess.run(x))
+writer.close() # close the writer when you’re done using it
+
+# Example 2: The wonderful wizard of div
+a = tf.constant([2, 2], name='a')
+b = tf.constant([[0, 1], [2, 3]], name='b')
+
+with tf.Session() as sess:
+    print(sess.run(tf.div(b, a)))
+    print(sess.run(tf.divide(b, a)))
+    print(sess.run(tf.truediv(b, a)))
+    print(sess.run(tf.floordiv(b, a)))
+    # print(sess.run(tf.realdiv(b, a)))
+    print(sess.run(tf.truncatediv(b, a)))
+    print(sess.run(tf.floor_div(b, a)))
+
+# Example 3: multiplying tensors
+a = tf.constant([10, 20], name='a')
+b = tf.constant([2, 3], name='b')
+
+with tf.Session() as sess:
+    print(sess.run(tf.multiply(a, b)))
+    print(sess.run(tf.tensordot(a, b, 1)))
+
+# Example 4: Python native type
+t_0 = 19 
+x = tf.zeros_like(t_0) 					# ==> 0
+y = tf.ones_like(t_0) 					# ==> 1
+
+t_1 = ['apple', 'peach', 'banana']
+x = tf.zeros_like(t_1) 					# ==> ['' '' '']
+# y = tf.ones_like(t_1) 				# ==> TypeError: Expected string, got 1 of type 'int' instead.
+
+t_2 = [[True, False, False],
+       [False, False, True],
+       [False, True, False]] 
+x = tf.zeros_like(t_2) 					# ==> 3x3 tensor, all elements are False
+y = tf.ones_like(t_2) 					# ==> 3x3 tensor, all elements are True
+
+print(tf.int32.as_numpy_dtype())
+
+# Example 5: printing your graph's definition
+my_const = tf.constant([1.0, 2.0], name='my_const')
+print(tf.get_default_graph().as_graph_def())

examples/02_variables.py

@@ -0,0 +1,71 @@
+""" Variable exmaples
+Created by Chip Huyen (huyenn@stanford.edu)
+CS20: "TensorFlow for Deep Learning Research"
+cs20.stanford.edu
+Lecture 02
+"""
+import os
+os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
+
+import numpy as np
+import tensorflow as tf
+
+# Example 1: creating variables
+s = tf.Variable(2, name='scalar') 
+m = tf.Variable([[0, 1], [2, 3]], name='matrix') 
+W = tf.Variable(tf.zeros([784,10]), name='big_matrix')
+V = tf.Variable(tf.truncated_normal([784, 10]), name='normal_matrix')
+
+s = tf.get_variable('scalar', initializer=tf.constant(2)) 
+m = tf.get_variable('matrix', initializer=tf.constant([[0, 1], [2, 3]]))
+W = tf.get_variable('big_matrix', shape=(784, 10), initializer=tf.zeros_initializer())
+V = tf.get_variable('normal_matrix', shape=(784, 10), initializer=tf.truncated_normal_initializer())
+
+with tf.Session() as sess:
+    sess.run(tf.global_variables_initializer())
+    print(V.eval())
+
+# Example 2: assigning values to variables
+W = tf.Variable(10)
+W.assign(100)
+with tf.Session() as sess:
+    sess.run(W.initializer)
+    print(sess.run(W))                    	# >> 10
+
+W = tf.Variable(10)
+assign_op = W.assign(100)
+with tf.Session() as sess:
+    sess.run(assign_op)
+    print(W.eval())                     	# >> 100
+
+# create a variable whose original value is 2
+a = tf.get_variable('scalar', initializer=tf.constant(2)) 
+a_times_two = a.assign(a * 2)
+with tf.Session() as sess:
+    sess.run(tf.global_variables_initializer()) 
+    sess.run(a_times_two)                 	# >> 4
+    sess.run(a_times_two)                 	# >> 8
+    sess.run(a_times_two)                 	# >> 16
+
+W = tf.Variable(10)
+with tf.Session() as sess:
+    sess.run(W.initializer)
+    print(sess.run(W.assign_add(10)))     	# >> 20
+    print(sess.run(W.assign_sub(2)))     	# >> 18
+
+# Example 3: Each session has its own copy of variable
+W = tf.Variable(10)
+sess1 = tf.Session()
+sess2 = tf.Session()
+sess1.run(W.initializer)
+sess2.run(W.initializer)
+print(sess1.run(W.assign_add(10)))        	# >> 20
+print(sess2.run(W.assign_sub(2)))        	# >> 8
+print(sess1.run(W.assign_add(100)))        	# >> 120
+print(sess2.run(W.assign_sub(50)))        	# >> -42
+sess1.close()
+sess2.close()
+
+# Example 4: create a variable with the initial value depending on another variable
+W = tf.Variable(tf.truncated_normal([700, 10]))
+U = tf.Variable(W * 2)