tf.clip_by_value() can clip a tenser values to min and max number. In this tutorial, we will write an example to display the result in three situation.
Here is an example code:
import tensorflow as tf; import numpy as np A = tf.constant([[1,2,3],[1,3,3],[4,5,6],[7,8,9]], dtype=tf.float32) B = tf.clip_by_value(A,2,7) # the max number in A is smaller than 10 C = tf.clip_by_value(A,10,15) # the min number in A is bigger than 0.5 D = tf.clip_by_value(A,0,0.5) 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) b, c, d = sess.run([B, C, D]) print 'b=' print b print 'c=' print c print 'b=' print d
The result is:
Note: You must pay attention to minimum and maximum value in tensor whether is in min or max of tf.clip_by_value().