conditional assignment of tf.variable in Tensorflow 2

user_5865579 0
Viewed 258

For numpy we have

threshold = 3
a = np.array([1,2,3,4,5,6])
a[a>=3] = 199

# a is [1, 2, 199, 199, 199, 199]

How to write a similar code in tensorflow 2

b = tf.Variable(a)

Thanks.

tensorflow2.0 conditional-statements python-3.x python
1 Answers

Sure, you can use tf.where to conditionally set values:

b = tf.Variable(a)
tf.where(b >= 3, 199, b)
# <tf.Tensor: shape=(6,), dtype=int64, numpy=array([  1,   2, 199, 199, 199, 199])>
user_49090870
Related