ML lec 02 - TensorFlow로 간단한 Linear regression을 구현

Review

 

(H(x) = predicted value, y = true value)

W와 b를 조정해서 cost를 minimize한다.

 

TensorFlow Mechanics

1. Build graph using

2. session run - 그래프 실행

3. graph update

 

1. Build graph using TF operations

# X and Y data
x_train = [1, 2, 3]
y_train = [1, 2, 3]

# 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")

# Our hypothesis XW+b
hypothesis = x_train * W + b

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

# optimizer
train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost)

 

2 and 3. Run / update graph and get results

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

# Fit the line
for step in ragne(2001):
	sess.run(train)
    if step % 20 == 0:
    	print(step, sess.run(cost), sess.run(W), sess.run(b))

 

Result

# 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]
...
1960 1.46397e-05 [ 1.004444] [-0.01010205]
1980 1.32962e-05 [ 1.00423515] [-0.00962736]
2000 1.20761e-05 [ 1.00403607] [-0.00917497]

---

Full code with Placeholders

# Lab 2 Linear Regression
import tensorflow as tf
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")

# placeholders for a tensor that will be always fed using feed_dict
# See http://stackoverflow.com/questions/36693740/
X = tf.placeholder(tf.float32, shape=[None])
Y = tf.placeholder(tf.float32, shape=[None])

# Our hypothesis is X * W + b
hypothesis = X * W + b

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

# optimizer
train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost)

# Launch the graph in a session.
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(
            [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)