code for lecture 5

Author: chiphuyen

.gitignore

@@ -4,3 +4,7 @@
 *.SUNet
 *.pyc
 .env/*
+examples/data/*
+examples/graphs/*
+examples/checkpoints/*
+examples/visualization/*

examples/04_word2vec_visualize.py

@@ -158,7 +158,7 @@ def visualize(self, visual_fld, num_visualize):
             embedding.tensor_name = embedding_var.name
 
             # link this tensor to its metadata file, in this case the first NUM_VISUALIZE words of vocab
-            embedding.metadata_path = os.path.join(visual_fld, 'vocab_' + str(num_visualize) + '.tsv')
+            embedding.metadata_path = 'vocab_' + str(num_visualize) + '.tsv'
 
             # saves a configuration file that TensorBoard will read during startup.
             projector.visualize_embeddings(summary_writer, config)

examples/05_randomization.py

@@ -0,0 +1,44 @@
+""" Examples to demonstrate ops level randomization
+CS 20: "TensorFlow for Deep Learning Research"
+cs20.stanford.edu
+Chip Huyen (chiphuyen@cs.stanford.edu)
+Lecture 05
+"""
+import os
+os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
+
+import tensorflow as tf
+
+# Example 1: session keeps track of the random state
+c = tf.random_uniform([], -10, 10, seed=2)
+
+with tf.Session() as sess:
+    print(sess.run(c)) # >> 3.574932
+    print(sess.run(c)) # >> -5.9731865
+
+# Example 2: each new session will start the random state all over again.
+c = tf.random_uniform([], -10, 10, seed=2)
+
+with tf.Session() as sess:
+    print(sess.run(c)) # >> 3.574932
+
+with tf.Session() as sess:
+    print(sess.run(c)) # >> 3.574932
+
+# Example 3: with operation level random seed, each op keeps its own seed.
+c = tf.random_uniform([], -10, 10, seed=2)
+d = tf.random_uniform([], -10, 10, seed=2)
+
+with tf.Session() as sess:
+    print(sess.run(c)) # >> 3.574932
+    print(sess.run(d)) # >> 3.574932
+
+# Example 4: graph level random seed
+tf.set_random_seed(2)
+c = tf.random_uniform([], -10, 10)
+d = tf.random_uniform([], -10, 10)
+
+with tf.Session() as sess:
+    print(sess.run(c)) # >> 9.123926
+    print(sess.run(d)) # >> -4.5340395
+    

examples/05_variable_sharing.py

@@ -0,0 +1,69 @@
+""" Examples to demonstrate variable sharing
+CS 20: 'TensorFlow for Deep Learning Research'
+cs20.stanford.edu
+Chip Huyen (chiphuyen@cs.stanford.edu)
+Lecture 05
+"""
+import os
+os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
+
+import tensorflow as tf
+
+x1 = tf.truncated_normal([200, 100], name='x1')
+x2 = tf.truncated_normal([200, 100], name='x2')
+
+def two_hidden_layers(x):
+    assert x.shape.as_list() == [200, 100]
+    w1 = tf.Variable(tf.random_normal([100, 50]), name='h1_weights')
+    b1 = tf.Variable(tf.zeros([50]), name='h1_biases')
+    h1 = tf.matmul(x, w1) + b1
+    assert h1.shape.as_list() == [200, 50]  
+    w2 = tf.Variable(tf.random_normal([50, 10]), name='h2_weights')
+    b2 = tf.Variable(tf.zeros([10]), name='2_biases')
+    logits = tf.matmul(h1, w2) + b2
+    return logits
+
+def two_hidden_layers_2(x):
+    assert x.shape.as_list() == [200, 100]
+    w1 = tf.get_variable('h1_weights', [100, 50], initializer=tf.random_normal_initializer())
+    b1 = tf.get_variable('h1_biases', [50], initializer=tf.constant_initializer(0.0))
+    h1 = tf.matmul(x, w1) + b1
+    assert h1.shape.as_list() == [200, 50]  
+    w2 = tf.get_variable('h2_weights', [50, 10], initializer=tf.random_normal_initializer())
+    b2 = tf.get_variable('h2_biases', [10], initializer=tf.constant_initializer(0.0))
+    logits = tf.matmul(h1, w2) + b2
+    return logits
+
+# logits1 = two_hidden_layers(x1)
+# logits2 = two_hidden_layers(x2)
+
+# logits1 = two_hidden_layers_2(x1)
+# logits2 = two_hidden_layers_2(x2)
+
+# with tf.variable_scope('two_layers') as scope:
+#     logits1 = two_hidden_layers_2(x1)
+#     scope.reuse_variables()
+#     logits2 = two_hidden_layers_2(x2)
+
+# with tf.variable_scope('two_layers') as scope:
+#     logits1 = two_hidden_layers_2(x1)
+#     scope.reuse_variables()
+#     logits2 = two_hidden_layers_2(x2)
+
+def fully_connected(x, output_dim, scope):
+    with tf.variable_scope(scope, reuse=tf.AUTO_REUSE) as scope:
+        w = tf.get_variable('weights', [x.shape[1], output_dim], initializer=tf.random_normal_initializer())
+        b = tf.get_variable('biases', [output_dim], initializer=tf.constant_initializer(0.0))
+        return tf.matmul(x, w) + b
+
+def two_hidden_layers(x):
+    h1 = fully_connected(x, 50, 'h1')
+    h2 = fully_connected(h1, 10, 'h2')
+
+with tf.variable_scope('two_layers') as scope:
+    logits1 = two_hidden_layers(x1)
+    # scope.reuse_variables()
+    logits2 = two_hidden_layers(x2)
+
+writer = tf.summary.FileWriter('./graphs/cool_variables', tf.get_default_graph())
+writer.close()

examples/word2vec_utils.py

@@ -61,7 +61,7 @@ def most_common_words(visual_fld, num_visualize):
     """
     words = open(os.path.join(visual_fld, 'vocab.tsv'), 'r').readlines()[:num_visualize]
     words = [word for word in words]
-    file = open(os.path.join(visual_fld, 'vocab_' + str(num_visualize) + '.tsv'), "w")
+    file = open(os.path.join(visual_fld, 'vocab_' + str(num_visualize) + '.tsv'), 'w')
     for word in words:
         file.write(word)
     file.close()