Compute Singular Value Decomposition (SVD) with TensorFlow – TensorFlow Example

In this tutorial, we will write an example for computing SVD value with TensorFlow. You can exercise this example by update our example code.

import tensorflow as tf;
import numpy as np
A = tf.constant([[1,2,3],[4,5,6],[7,8,9]], dtype=tf.float32)

s, u, v = tf.svd(A)

A2 = tf.matmul(tf.matmul(u, tf.diag(s)), tf.transpose(v))

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)
   
    s, u, v,a2 = (sess.run([s, u, v, A2]))
    print 's='
    print s
    print 'u='
    print u
    print 'v='
    print v
    print 'A='
    print a2

Notice:

You must know we also can caculate SVD in Numpy and you should know the difference between them, especial for V matrix.