tf.reduce_prod(): Compute the Product of All Elements in a Tensor By Axis – TensorFlow Tutorial

In this tutorial, we will use an example to show you how to use tf.reduce_prod() correctly. This function is very similar to tf.reduce_mean() or tf.reduce_sum().

Syntax

tf.reduce_prod() is defined as:

tf.reduce_prod(
    input_tensor,
    axis=None,
    keepdims=None,
    name=None,
    reduction_indices=None,
    keep_dims=None
)

It can compute the product of elements across dimensions of a tensor.

Parameters:

input_tensor: the tensor we will pass

axis: the dimensions to compute. If None (the default), compute all dimensions

keepdims: If true, retains computed dimensions with length 1

How to use tf.reduce_prod()?

Here is an example:

import tensorflow as tf
import numpy as np
data = tf.convert_to_tensor(np.array([[2,3,4],[3,2,2]]), dtype = tf.float32)

re = tf.reduce_prod(data, axis= - 1)
init = tf.global_variables_initializer()
init_local = tf.local_variables_initializer()
with tf.Session() as sess:
    sess.run([init, init_local])
    np.set_printoptions(precision=4, suppress=True)
    a =sess.run(re) 
    print(a)

Here data is 2*3, we will compute the product of elements on axis = -1.

Run this code, we will see:

[24. 12.]

If we ignore axis, we will get:

re = tf.reduce_prod(data)

The final result is: 288.0