Updated lab07 files

lab-07-1-learning_rate_and_evaluation.py

@@ -26,7 +26,8 @@
 # Cross entropy cost/loss
 cost = tf.reduce_mean(-tf.reduce_sum(Y * tf.log(hypothesis), axis=1))
 # Try to change learning_rate to small numbers
-optimizer = tf.train.GradientDescentOptimizer(learning_rate=1.5).minimize(cost)
+optimizer = tf.train.GradientDescentOptimizer(
+    learning_rate=1e-10).minimize(cost)
 
 # Correct prediction Test model
 prediction = tf.arg_max(hypothesis, 1)
@@ -76,6 +77,30 @@
 Prediction: [0 0 0]
 Accuracy:  0.0
 
+-------------------------------------------------
+When lr = 1e-10
+0 5.73203 [[ 0.80269563  0.67861295 -1.21728313]
+ [-0.3051686  -0.3032113   1.50825703]
+ [ 0.75722361 -0.7008909  -2.10820389]]
+1 5.73203 [[ 0.80269563  0.67861295 -1.21728313]
+ [-0.3051686  -0.3032113   1.50825703]
+ [ 0.75722361 -0.7008909  -2.10820389]]
+2 5.73203 [[ 0.80269563  0.67861295 -1.21728313]
+ [-0.3051686  -0.3032113   1.50825703]
+ [ 0.75722361 -0.7008909  -2.10820389]]
+...
+
+198 5.73203 [[ 0.80269563  0.67861295 -1.21728313]
+ [-0.3051686  -0.3032113   1.50825703]
+ [ 0.75722361 -0.7008909  -2.10820389]]
+199 5.73203 [[ 0.80269563  0.67861295 -1.21728313]
+ [-0.3051686  -0.3032113   1.50825703]
+ [ 0.75722361 -0.7008909  -2.10820389]]
+200 5.73203 [[ 0.80269563  0.67861295 -1.21728313]
+ [-0.3051686  -0.3032113   1.50825703]
+ [ 0.75722361 -0.7008909  -2.10820389]]
+Prediction: [0 0 0]
+Accuracy:  0.0
 -------------------------------------------------
 When lr = 0.1
 

lab-07-2-linear_regression_without_min_max.py

@@ -114,4 +114,4 @@
  [ nan]
  [ nan]
  [ nan]]
-'''
+'''

lab-07-3-linear_regression_min_max.py

@@ -65,4 +65,4 @@ def MinMaxScaler(data):
  [ 0.23175186]
  [-0.13716528]]
 
-'''
+'''

lab-07-4-mnist_introduction.py

@@ -2,6 +2,7 @@
 import tensorflow as tf
 import random
 import matplotlib.pyplot as plt
+tf.set_random_seed(777)  # for reproducibility
 
 from tensorflow.examples.tutorials.mnist import input_data
 # Check out https://www.tensorflow.org/get_started/mnist/beginners for
@@ -10,42 +11,41 @@
 
 nb_classes = 10
 
-W = tf.Variable(tf.zeros([784, nb_classes]))
-b = tf.Variable(tf.zeros([nb_classes]))
-
-# parameters
-training_epochs = 15
-batch_size = 100
-
 # MNIST data image of shape 28 * 28 = 784
 X = tf.placeholder(tf.float32, [None, 784])
 # 0 - 9 digits recognition = 10 classes
 Y = tf.placeholder(tf.float32, [None, nb_classes])
 
+W = tf.Variable(tf.random_normal([784, nb_classes]))
+b = tf.Variable(tf.random_normal([nb_classes]))
+
 # Hypothesis (using softmax)
 hypothesis = tf.nn.softmax(tf.matmul(X, W) + b)
 
 cost = tf.reduce_mean(-tf.reduce_sum(Y * tf.log(hypothesis), axis=1))
-optimizer = tf.train.GradientDescentOptimizer(learning_rate=1.).minimize(cost)
+optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.1).minimize(cost)
 
 # Test model
 is_correct = tf.equal(tf.arg_max(hypothesis, 1), tf.arg_max(Y, 1))
 # Calculate accuracy
 accuracy = tf.reduce_mean(tf.cast(is_correct, tf.float32))
 
+# parameters
+training_epochs = 15
+batch_size = 100
+
 with tf.Session() as sess:
     # Initialize TensorFlow variables
     sess.run(tf.global_variables_initializer())
-
     # Training cycle
     for epoch in range(training_epochs):
         avg_cost = 0
         total_batch = int(mnist.train.num_examples / batch_size)
 
         for i in range(total_batch):
             batch_xs, batch_ys = mnist.train.next_batch(batch_size)
-            feed_dict = {X: batch_xs, Y: batch_ys}
-            c, _ = sess.run([cost, optimizer], feed_dict=feed_dict)
+            c, _ = sess.run([cost, optimizer], feed_dict={
+                            X: batch_xs, Y: batch_ys})
             avg_cost += c / total_batch
 
         print('Epoch:', '%04d' % (epoch + 1),
@@ -69,23 +69,21 @@
 
 
 '''
-Epoch: 0001 cost = 1.653421078
-Epoch: 0002 cost = 1.578180347
-Epoch: 0003 cost = 1.567036718
-Epoch: 0004 cost = 1.560953102
-Epoch: 0005 cost = 1.557037002
-Epoch: 0006 cost = 1.553987361
-Epoch: 0007 cost = 1.551654525
-Epoch: 0008 cost = 1.549694977
-Epoch: 0009 cost = 1.548126057
-Epoch: 0010 cost = 1.546662330
-Epoch: 0011 cost = 1.545407041
-Epoch: 0012 cost = 1.544319339
-Epoch: 0013 cost = 1.543301272
-Epoch: 0014 cost = 1.542362210
-Epoch: 0015 cost = 1.541643034
+Epoch: 0001 cost = 2.868104637
+Epoch: 0002 cost = 1.134684615
+Epoch: 0003 cost = 0.908220728
+Epoch: 0004 cost = 0.794199896
+Epoch: 0005 cost = 0.721815854
+Epoch: 0006 cost = 0.670184430
+Epoch: 0007 cost = 0.630576546
+Epoch: 0008 cost = 0.598888191
+Epoch: 0009 cost = 0.573027079
+Epoch: 0010 cost = 0.550497213
+Epoch: 0011 cost = 0.532001859
+Epoch: 0012 cost = 0.515517795
+Epoch: 0013 cost = 0.501175288
+Epoch: 0014 cost = 0.488425370
+Epoch: 0015 cost = 0.476968593
 Learning finished
-Accuracy:  0.9275
-Label:  [0]
-Prediction:  [0]
+Accuracy:  0.888
 '''