딥러닝의 기본 학습 - How to minimize cost-실습-2

import tensorflow as tf
X = [1, 2, 3]
Y = [1, 2, 3]

# Set wrong model weights
W = tf.Variable(5.)

# Linear model
hypothesis = X * W

# Manual gradient
gradient = tf.reduce_mean((W * X - Y) * X) * 2

# cost/loss function
cost = tf.reduce_mean(tf.square(hypothesis - Y))
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01)

# Get gradients
gvs = optimizer.compute_gradients(cost, [W])

# Apply gradients
apply_gradients = optimizer.apply_gradients(gvs)

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

for step in range(100):
   print(step, sess.run([gradient, W, gvs]))
   sess.run(apply_gradients)