ompile given code and as save 201916719 and take a picture with out put then send it to me import tensorflow as tf
ompile given code and as save 201916719 and take a picture with out put then send it to me
import tensorflow as tf
# x and y data
x_train = [1,2,3]
y_train = [1,2,3]
# try to find the optimal vakue for W and b that compute y= W * x + buffer
# (Altough we know that W and b should be 1 and 0,
# we conduct this procedure to check Tensorflow will find optimalk value)
# Initial value of WQ and b is set at the random value from the random function.
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))
# minimize
optimizer = tf.train.GradientDescentOptimizer(lkearning_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())
# Fit the line
for step in range(2001):
sess.run(train)
if step % 20 == 0:
print(step, sess.run(cost), sess.run(W), sess.run(b))
Step by step
Solved in 2 steps with 5 images
