CODEWITHSUNDEEP
pythontensorflow
swmfg
swmfg

Reputation: 1359

Keep changing the same variable in Tensorflow

I have a complicated use case which I've distilled down to just incrementing a variable in Tensorflow.

a = tf.Variable(1, trainable=False)
b = tf.constant(2)
a = tf.assign_add(a, b)
In [32]: type(a)
Out[32]: tensorflow.python.framework.ops.Tensor

My actual use case is actually generating a new random tensor under certain conditions each time my custom Keras layer is called, but seems like it boils down to a variable turning into a tensor if I do anything to it. Is the correct use case to wrap each a = tf.Variable(tf.assign(a, b)) and have a change everytime my keras layer is called?

Upvotes: 0

Views: 110

Answers (1)

P-Gn
P-Gn

Reputation: 24581

You are overthinking it. tf.assign_add returns an op that adds to a variable. The fact that it also return the resulting value is for convenience only — the variable is affected.

Example:

import tensorflow as tf

a = tf.Variable(1, trainable=False)
b = tf.constant(2)
c = tf.assign_add(a, b)

sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
print(sess.run(a))
# 1: the original value
print(sess.run(c))
# 3: the result of the addition
print(sess.run(a))
# 3: OK, the variable has indeed been added to

Upvotes: 1

Related Questions