In previous post we have seen how tensorflow works. Now let’s understand one of the integral component i.e tensorflow variable. A tensorflow variables are used to represent the weights in neural network !
# create a tensorflow variable
var = tf.Variable(0)
cons = tf.constant(1)
We shall update the value of the variable var and there by understanding the working of tensorflow variable.
sum = tf.add(var, cons)
assign =tf.assign(var, sum)
The construction phase is completed. Let’s start the session.
with tf.Sesstion() as sess:
print ‘var:’, sess.run(var), ‘cons:’, sess.run(cons)
for _ in range(3):
print ‘updated var:’, sess.run(var)
All variables are initialised in the graph by running sess.run(tf.initialise_all_varialbles).
var: 0 cons: 1
This is a small post and very specific. As tensorflow variables are very important I wanted to give a clear explanation of their working. Now, We can actually start building our own neural network ! We will using mnist dataset provided by tensorflow.org. The data is the format that is accepted by tensorflow. Therefore we need not to preprocess any data ! We shall train and test our first neural network in next !