TensorFlow 1.x Deep Learning Cookbook

 How to do it...

Let us now see how to proceed with the recipe:

1. In the case of standard linear regression, we have only one input variable and one output variable:

# Placeholder for the Training DataX = tf.placeholder(tf.float32, name='X')Y = tf.placeholder(tf.float32, name='Y')# Variables for coefficients initialized to 0w0 = tf.Variable(0.0)w1 = tf.Variable(0.0)# The Linear Regression ModelY_hat = X*w1 + w0# Loss functionloss = tf.square(Y - Y_hat, name=’loss’)

2. In the case of multiple linear regression, the input variables are more than one, while the output variable remains one. Now you can define X placeholder of shape [m, n], where m is the number of samples and n is the number of features, then the code is as follows:

# Placeholder ...