icehongssii/linear_regression_tf.py

## linear_regression_tf.py
import tensorflow as tf

x_train = [1,2,3]
y_train = [1,2,3]

# H(x) = Wx+b

W = tf.Variable(tf.random_normal([1]), name="weight")
b = tf.Variable(tf.random_normal([1]), name="bias")

#our hypo
hypothesis = x_train*W+b

#cost(w,b) 제곱차
cost = tf.reduce_mean(tf.square(hypothesis-y_train))

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

#그래프 실행위한 세션만들기
sess = tf.Session()

# to use W,b, it has to be initialized first
sess.run(tf.global_variables_initializer())

#train 노드가 실행시켜야함 cost, hypto, w,b모두 실행시킬 수 있다

for step in range(2001):
    sess.run(train)
    if step % 20 == 0 :
        print(step,sess.run(cost),sess.run(W), sess.run(b))
	import tensorflow as tf

	x_train = [1,2,3]
	y_train = [1,2,3]

	# H(x) = Wx+b

	W = tf.Variable(tf.random_normal([1]), name="weight")
	b = tf.Variable(tf.random_normal([1]), name="bias")

	#our hypo
	hypothesis = x_train*W+b

	#cost(w,b) 제곱차
	cost = tf.reduce_mean(tf.square(hypothesis-y_train))

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

	#그래프 실행위한 세션만들기
	sess = tf.Session()

	# to use W,b, it has to be initialized first
	sess.run(tf.global_variables_initializer())

	#train 노드가 실행시켜야함 cost, hypto, w,b모두 실행시킬 수 있다

	for step in range(2001):
	sess.run(train)
	if step % 20 == 0 :
	print(step,sess.run(cost),sess.run(W), sess.run(b))