What is the difference between np.mean and tf.reduce_mean?

Question

In the MNIST beginner tutorial, there is the statement

accuracy = tf.reduce_mean(tf.cast(correct_prediction, \"float\"))

tf.cast

Answer 1

The new documentation states that tf.reduce_mean() produces the same results as np.mean:

Equivalent to np.mean

It also has absolutely the same parameters as np.mean. But here is an important difference: they produce the same results only on float values:

import tensorflow as tf
import numpy as np
from random import randint

num_dims = 10
rand_dim = randint(0, num_dims - 1)
c = np.random.randint(50, size=tuple([5] * num_dims)).astype(float)

with tf.Session() as sess:
    r1 = sess.run(tf.reduce_mean(c, rand_dim))
    r2 = np.mean(c, rand_dim)
    is_equal = np.array_equal(r1, r2)
    print is_equal
    if not is_equal:
        print r1
        print r2

If you will remove type conversion, you will see different results

---

In additional to this, many other tf.reduce_ functions such as reduce_all, reduce_any, reduce_min, reduce_max, reduce_prod produce the same values as there numpy analogs. Clearly because they are operations, they can be executed only from inside of the session.