linear_model.py

import tensorflow as tf

weights = tf.Variable([1., 2., 3.],tf.float32)
biases = tf.Variable([4., 5., 6.], tf.float32)

x = tf.placeholder(tf.float32)

sess = tf.Session()

linear_model = weights * x + biases
sess.run(tf.global_variables_initializer())

y = tf.placeholder(tf.float32)
squared_deltas = tf.square(linear_model - y)
loss = tf.reduce_sum(squared_deltas)

optimizer = tf.train.GradientDescentOptimizer(0.01)
train = optimizer.minimize(loss)


print(sess.run([loss, weights, biases], {x:[1,2,3], y:[0,-1,-2]}))

for i in range(1000):
  sess.run(train, {x:[1,2,3], y:[0,-1,-2]})

print(sess.run([loss, weights, biases], {x:[1,2,3], y:[0,-1,-2]}))