tf_linear_regression.py

import tensorflow as tf
import numpy

# Parameters
learning_rate = 0.01
training_epochs = 5300
datapoints_count = 100

# Training Data
train_X = []
train_Y = []
for i in range(datapoints_count):
  train_X.append(i)
  train_Y.append(5*i+8.0)

train_X = numpy.asarray(train_X)
train_Y = numpy.asarray(train_Y)
n_samples = train_X.shape[0]

# tf Graph Input
X = tf.placeholder("float")
Y = tf.placeholder("float")

# Set model weights
W = tf.Variable(0.0, name="weight")
b = tf.Variable(0.0, name="bias")

# Construct a linear model
y_pred = X * W + b

# Mean squared error
cost = tf.reduce_sum(tf.square(y_pred-Y))/(2*n_samples)

# Gradient descent
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

# Start training
with tf.Session() as sess:
  sess.run(tf.global_variables_initializer())

  # Fit all training data
  for epoch in range(training_epochs):
    for (x, y) in zip(train_X, train_Y):
      sess.run(optimizer, feed_dict={X: x, Y: y})

    # Display logs for every 50 epoch step
    if (epoch+1) % 50 == 0:
      c = sess.run(cost, feed_dict={X: train_X, Y:train_Y})
      print("Epoch: %04d cost=%.9f W=%f b=%f" % \
        ((epoch+1), c, sess.run(W), sess.run(b)))

  training_cost = sess.run(cost, feed_dict={X: train_X, Y: train_Y})
  print("Training cost=%.9f W=%f b=%f" % \
    (training_cost, sess.run(W), sess.run(b)))