lossFunction.py

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

x_train = np.linspace(0, 10, 100)
y_train = x_train + np.random.normal(0,1,100)

learning_rate = 0.01
training_epoches = 100

X = tf.placeholder(tf.float32)
Y = tf.placeholder(tf.float32)

w0 = tf.Variable(0.0, name="W0")
w1 = tf.Variable(0.0, name="W1")


# f(xi) = xi*w1 + w0
def f(X, w1, w0):
       return tf.add(tf.multiply(X, w1), w0)
f_xi = f(X, w1, w0)
# loss function
lossF = tf.square(Y-f_xi)

train_op = tf.train.GradientDescentOptimizer(learning_rate).minimize(lossF)

sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)

for epoch in range(training_epoches):
       for (x, y) in zip(x_train, y_train):
              sess.run(train_op, feed_dict={X: x, Y: y})


w_val_0 = sess.run(w0)
w_val_1 = sess.run(w1)
sess.close()

plt.scatter(x_train, y_train)

y_learned = x_train*w_val_1 + w_val_0
plt.plot(x_train, y_learned, 'r')
plt.show()