Update Lab-02, Lab-03 (hunkim#240)

* Update lab-03-X-minimizing_cost_tf_gradient.py

1. The value of W changes because of 'apply_gradients', not because of 'gradient'. Therefore, it is not necessary to make W output twice.
2. Modified output comment.
3. 'train = optimizer.minimize (cost)' is an unnecessary sentence.

* Modify the code for readability. (Black formatting)

Author: qoocrab

lab-02-1-linear_regression.py

@@ -9,41 +9,37 @@
 # Try to find values for W and b to compute y_data = x_data * W + b
 # We know that W should be 1 and b should be 0
 # But let TensorFlow figure it out
-W = tf.Variable(tf.random_normal([1]), name='weight')
-b = tf.Variable(tf.random_normal([1]), name='bias')
+W = tf.Variable(tf.random_normal([1]), name="weight")
+b = tf.Variable(tf.random_normal([1]), name="bias")
 
 # Our hypothesis XW+b
 hypothesis = x_train * W + b
 
 # cost/loss function
 cost = tf.reduce_mean(tf.square(hypothesis - y_train))
 
-# Minimize
-optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01)
-train = optimizer.minimize(cost)
+# optimizer
+train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost)
 
 # Launch the graph in a session.
-sess = tf.Session()
-# Initializes global variables in the graph.
-sess.run(tf.global_variables_initializer())
+with tf.Session() as sess:
+    # Initializes global variables in the graph.
+    sess.run(tf.global_variables_initializer())
 
-# Fit the line
-for step in range(2001):
-    sess.run(train)
-    if step % 20 == 0:
-        print(step, sess.run(cost), sess.run(W), sess.run(b))
+    # Fit the line
+    for step in range(2001):
+        _, cost_val, W_val, b_val = sess.run([train, cost, W, b])
 
-# Learns best fit W:[ 1.],  b:[ 0.]
+        if step % 20 == 0:
+            print(step, cost_val, W_val, b_val)
 
-'''
+# Learns best fit W:[ 1.],  b:[ 0.]
+"""
 0 2.82329 [ 2.12867713] [-0.85235667]
 20 0.190351 [ 1.53392804] [-1.05059612]
 40 0.151357 [ 1.45725465] [-1.02391243]
 ...
-
-1920 1.77484e-05 [ 1.00489295] [-0.01112291]
-1940 1.61197e-05 [ 1.00466311] [-0.01060018]
 1960 1.46397e-05 [ 1.004444] [-0.01010205]
 1980 1.32962e-05 [ 1.00423515] [-0.00962736]
 2000 1.20761e-05 [ 1.00403607] [-0.00917497]
-'''
+"""

lab-02-2-linear_regression_feed.py

@@ -3,8 +3,8 @@
 tf.set_random_seed(777)  # for reproducibility
 
 # Try to find values for W and b to compute Y = W * X + b
-W = tf.Variable(tf.random_normal([1]), name='weight')
-b = tf.Variable(tf.random_normal([1]), name='bias')
+W = tf.Variable(tf.random_normal([1]), name="weight")
+b = tf.Variable(tf.random_normal([1]), name="bias")
 
 # placeholders for a tensor that will be always fed using feed_dict
 # See http://stackoverflow.com/questions/36693740/
@@ -17,64 +17,61 @@
 # cost/loss function
 cost = tf.reduce_mean(tf.square(hypothesis - Y))
 
-# Minimize
-optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01)
-train = optimizer.minimize(cost)
+# optimizer
+train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost)
 
 # Launch the graph in a session.
-sess = tf.Session()
-# Initializes global variables in the graph.
-sess.run(tf.global_variables_initializer())
+with tf.Session() as sess:
+    # Initializes global variables in the graph.
+    sess.run(tf.global_variables_initializer())
 
-# Fit the line
-for step in range(2001):
-    cost_val, W_val, b_val, _ = \
-        sess.run([cost, W, b, train],
-                 feed_dict={X: [1, 2, 3], Y: [1, 2, 3]})
-    if step % 20 == 0:
-        print(step, cost_val, W_val, b_val)
+    # Fit the line
+    for step in range(2001):
+        _, cost_val, W_val, b_val = sess.run(
+            [train, cost, W, b], feed_dict={X: [1, 2, 3], Y: [1, 2, 3]}
+        )
+        if step % 20 == 0:
+            print(step, cost_val, W_val, b_val)
 
-# Learns best fit W:[ 1.],  b:[ 0]
-'''
-...
-1980 1.32962e-05 [ 1.00423515] [-0.00962736]
-2000 1.20761e-05 [ 1.00403607] [-0.00917497]
-'''
+    # Testing our model
+    print(sess.run(hypothesis, feed_dict={X: [5]}))
+    print(sess.run(hypothesis, feed_dict={X: [2.5]}))
+    print(sess.run(hypothesis, feed_dict={X: [1.5, 3.5]}))
 
-# Testing our model
-print(sess.run(hypothesis, feed_dict={X: [5]}))
-print(sess.run(hypothesis, feed_dict={X: [2.5]}))
-print(sess.run(hypothesis, feed_dict={X: [1.5, 3.5]}))
+    # Learns best fit W:[ 1.],  b:[ 0]
+    """
+    0 3.5240757 [2.2086694] [-0.8204183]
+    20 0.19749963 [1.5425726] [-1.0498911]
+    ...
+    1980 1.3360998e-05 [1.0042454] [-0.00965055]
+    2000 1.21343355e-05 [1.0040458] [-0.00919707]
+    [5.0110054]
+    [2.500915]
+    [1.4968792 3.5049512]
+    """
 
-'''
-[ 5.0110054]
-[ 2.50091505]
-[ 1.49687922  3.50495124]
-'''
+    # Fit the line with new training data
+    for step in range(2001):
+        _, cost_val, W_val, b_val = sess.run(
+            [train, cost, W, b],
+            feed_dict={X: [1, 2, 3, 4, 5], Y: [2.1, 3.1, 4.1, 5.1, 6.1]},
+        )
+        if step % 20 == 0:
+            print(step, cost_val, W_val, b_val)
 
+    # Testing our model
+    print(sess.run(hypothesis, feed_dict={X: [5]}))
+    print(sess.run(hypothesis, feed_dict={X: [2.5]}))
+    print(sess.run(hypothesis, feed_dict={X: [1.5, 3.5]}))
 
-# Fit the line with new training data
-for step in range(2001):
-    cost_val, W_val, b_val, _ = \
-        sess.run([cost, W, b, train],
-                 feed_dict={X: [1, 2, 3, 4, 5],
-                            Y: [2.1, 3.1, 4.1, 5.1, 6.1]})
-    if step % 20 == 0:
-        print(step, cost_val, W_val, b_val)
-
-# Learns best fit W:[ 1.],  b:[ 1.1]
-'''
-1980 2.90429e-07 [ 1.00034881] [ 1.09874094]
-2000 2.5373e-07 [ 1.00032604] [ 1.09882331]
-'''
-
-# Testing our model
-print(sess.run(hypothesis, feed_dict={X: [5]}))
-print(sess.run(hypothesis, feed_dict={X: [2.5]}))
-print(sess.run(hypothesis, feed_dict={X: [1.5, 3.5]}))
-
-'''
-[ 6.10045338]
-[ 3.59963846]
-[ 2.59931231  4.59996414]
-'''
+    # Learns best fit W:[ 1.],  b:[ 1.1]
+    """
+    0 1.2035878 [1.0040361] [-0.00917497]
+    20 0.16904518 [1.2656431] [0.13599995]
+    ...
+    1980 2.9042917e-07 [1.00035] [1.0987366]
+    2000 2.5372992e-07 [1.0003271] [1.0988194]
+    [6.1004534]
+    [3.5996385]
+    [2.5993123 4.599964 ]
+    """

lab-02-3-linear_regression_tensorflow.org.py

@@ -1,34 +1,37 @@
 # From https://www.tensorflow.org/get_started/get_started
 import tensorflow as tf
 
+# training data
+x_train = [1, 2, 3, 4]
+y_train = [0, -1, -2, -3]
+
 # Model parameters
-W = tf.Variable([.3], tf.float32)
-b = tf.Variable([-.3], tf.float32)
+W = tf.Variable([0.3], tf.float32)
+b = tf.Variable([-0.3], tf.float32)
 
 # Model input and output
 x = tf.placeholder(tf.float32)
 y = tf.placeholder(tf.float32)
 
-linear_model = x * W + b
+hypothesis = x * W + b
 
 # cost/loss function
-loss = tf.reduce_sum(tf.square(linear_model - y))  # sum of the squares
+cost = tf.reduce_sum(tf.square(hypothesis - y))  # sum of the squares
 
 # optimizer
-optimizer = tf.train.GradientDescentOptimizer(0.01)
-train = optimizer.minimize(loss)
+train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost)
 
-# training data
-x_train = [1, 2, 3, 4]
-y_train = [0, -1, -2, -3]
+# training
+with tf.Session() as sess:
+    sess.run(tf.global_variables_initializer())
+
+    for step in range(1000):
+        sess.run(train, {x: x_train, y: y_train})
 
-# training loop
-init = tf.global_variables_initializer()
-sess = tf.Session()
-sess.run(init)  # reset values to wrong
-for i in range(1000):
-    sess.run(train, {x: x_train, y: y_train})
+    # evaluate training accuracy
+    W_val, b_val, cost_val = sess.run([W, b, cost], feed_dict={x: x_train, y: y_train})
+    print(f"W: {W_val} b: {b_val} cost: {cost_val}")
 
-# evaluate training accuracy
-curr_W, curr_b, curr_loss = sess.run([W, b, loss], {x: x_train, y: y_train})
-print("W: %s b: %s loss: %s" % (curr_W, curr_b, curr_loss))
+"""
+W: [-0.9999969] b: [0.9999908] cost: 5.699973826267524e-11
+"""

lab-03-1-minimizing_cost_show_graph.py

@@ -1,7 +1,6 @@
 # Lab 3 Minimizing Cost
 import tensorflow as tf
 import matplotlib.pyplot as plt
-tf.set_random_seed(777)  # for reproducibility
 
 X = [1, 2, 3]
 Y = [1, 2, 3]
@@ -14,18 +13,18 @@
 # cost/loss function
 cost = tf.reduce_mean(tf.square(hypothesis - Y))
 
-# Launch the graph in a session.
-sess = tf.Session()
-
 # Variables for plotting cost function
 W_history = []
 cost_history = []
 
-for i in range(-30, 50):
-    curr_W = i * 0.1
-    curr_cost = sess.run(cost, feed_dict={W: curr_W})
-    W_history.append(curr_W)
-    cost_history.append(curr_cost)
+# Launch the graph in a session.
+with tf.Session() as sess:
+    for i in range(-30, 50):
+        curr_W = i * 0.1
+        curr_cost = sess.run(cost, feed_dict={W: curr_W})
+
+        W_history.append(curr_W)
+        cost_history.append(curr_cost)
 
 # Show the cost function
 plt.plot(W_history, cost_history)

lab-03-2-minimizing_cost_gradient_update.py

@@ -1,5 +1,6 @@
 # Lab 3 Minimizing Cost
 import tensorflow as tf
+
 tf.set_random_seed(777)  # for reproducibility
 
 x_data = [1, 2, 3]
@@ -8,7 +9,7 @@
 # Try to find values for W and b to compute y_data = W * x_data
 # We know that W should be 1
 # But let's use TensorFlow to figure it out
-W = tf.Variable(tf.random_normal([1]), name='weight')
+W = tf.Variable(tf.random_normal([1]), name="weight")
 
 X = tf.placeholder(tf.float32)
 Y = tf.placeholder(tf.float32)
@@ -26,15 +27,17 @@
 update = W.assign(descent)
 
 # Launch the graph in a session.
-sess = tf.Session()
-# Initializes global variables in the graph.
-sess.run(tf.global_variables_initializer())
+with tf.Session() as sess:
+    # Initializes global variables in the graph.
+    sess.run(tf.global_variables_initializer())
 
-for step in range(21):
-    _, cost_val, W_val = sess.run([update, cost, W], feed_dict={X: x_data, Y: y_data})
-    print(step, cost_val, W_val)
+    for step in range(21):
+        _, cost_val, W_val = sess.run(
+            [update, cost, W], feed_dict={X: x_data, Y: y_data}
+        )
+        print(step, cost_val, W_val)
 
-'''
+"""
 0 1.93919 [ 1.64462376]
 1 0.551591 [ 1.34379935]
 2 0.156897 [ 1.18335962]
@@ -56,4 +59,4 @@
 18 2.88878e-10 [ 1.00000787]
 19 8.02487e-11 [ 1.00000417]
 20 2.34053e-11 [ 1.00000226]
-'''
+"""

lab-03-3-minimizing_cost_tf_optimizer.py

@@ -1,6 +1,5 @@
 # Lab 3 Minimizing Cost
 import tensorflow as tf
-tf.set_random_seed(777)  # for reproducibility
 
 # tf Graph Input
 X = [1, 2, 3]
@@ -15,28 +14,27 @@
 # cost/loss function
 cost = tf.reduce_mean(tf.square(hypothesis - Y))
 
-# Minimize: Gradient Descent Magic
-optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.1)
-train = optimizer.minimize(cost)
+# Minimize: Gradient Descent Optimizer
+train = tf.train.GradientDescentOptimizer(learning_rate=0.1).minimize(cost)
 
 # Launch the graph in a session.
-sess = tf.Session()
-# Initializes global variables in the graph.
-sess.run(tf.global_variables_initializer())
+with tf.Session() as sess:
+    # Initializes global variables in the graph.
+    sess.run(tf.global_variables_initializer())
 
-for step in range(100):
-    W_val, _ = sess.run([W, train])
-    print(step, W_val)
+    for step in range(101):
+        _, W_val = sess.run([train, W])
+        print(step, W_val)
 
-'''
+"""
 0 5.0
-1 1.26667
-2 1.01778
-3 1.00119
-4 1.00008
+1 1.2666664
+2 1.0177778
+3 1.0011852
+4 1.000079
 ...
-96 1.0
 97 1.0
 98 1.0
 99 1.0
-'''
+100 1.0
+"""