notebook.community

Edit and run



In [1]:

    
import tensorflow as tf
import matplotlib.pyplot as plt



In [4]:

    
tf.set_random_seed(777)  # for reproducibility

X = [1, 2, 3]
Y = [1, 2, 3]

W = tf.placeholder(tf.float32)

# Our hypothesis for linear model X * W
hypothesis = X * W

# cost/loss function
cost = tf.reduce_mean(tf.square(hypothesis - Y))

# Launch the graph in a session.
sess = tf.Session()
# Initializes global variables in the graph.
sess.run(tf.global_variables_initializer())

# Variables for plotting cost function 그래프를 그리기위해 
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)

# Show the cost function
plt.plot(W_history, cost_history)
plt.xlabel("W")
plt.ylabel("cost(W)")
plt.show()



In [8]:

    
x_data = [1, 2, 3]
y_data = [1, 2, 3]

# Try to find values for W and b to compute y_data = W * x_data + b
# We know that W should be 1 and b should be 0
# But let's use TensorFlow to figure it out
W = tf.Variable(tf.random_normal([1]), name='weight')

X = tf.placeholder(tf.float32)
Y = tf.placeholder(tf.float32)

# Our hypothesis for linear model X * W
hypothesis = X * W

# cost/loss function
cost = tf.reduce_mean(tf.square(hypothesis - Y))

# Minimize: Gradient Descent using derivative: W -= learning_rate * derivative
learning_rate = 0.1
gradient = tf.reduce_mean((W * X - Y) * X)
descent = W - learning_rate * gradient
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())

for step in range(21):
    sess.run(update, feed_dict={X: x_data, Y: y_data})
    print(step, sess.run(cost, feed_dict={X: x_data, Y: y_data}), sess.run(W))









    



0 6.69832 [-0.19806242]
1 1.9053 [ 0.36103338]
2 0.541952 [ 0.65921783]
3 0.154155 [ 0.81824952]
4 0.0438486 [ 0.9030664]
5 0.0124725 [ 0.94830209]
6 0.00354773 [ 0.97242779]
7 0.00100913 [ 0.98529482]
8 0.000287043 [ 0.99215722]
9 8.16477e-05 [ 0.99581718]
10 2.32237e-05 [ 0.99776918]
11 6.60604e-06 [ 0.99881023]
12 1.87891e-06 [ 0.99936545]
13 5.34432e-07 [ 0.99966156]
14 1.52012e-07 [ 0.99981952]
15 4.32312e-08 [ 0.99990374]
16 1.22967e-08 [ 0.99994868]
17 3.48969e-09 [ 0.99997264]
18 9.96916e-10 [ 0.9999854]
19 2.83588e-10 [ 0.99999219]
20 8.02487e-11 [ 0.99999583]



In [10]:

    
tf.set_random_seed(777)  # for reproducibility

# tf Graph Input
X = [1, 2, 3]
Y = [1, 2, 3]

# Set wrong model weights
W = tf.Variable(-3.0)

# Linear model
hypothesis = X * W

# 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)

# Launch the graph in a session.
sess = tf.Session()
# Initializes global variables in the graph.
sess.run(tf.global_variables_initializer())

for step in range(100):
    print(step, sess.run(W))
    sess.run(train)