tf.math.sqrt

TensorFlow 1 version View source on GitHub

Computes element-wise square root of the input tensor.

tf.math.sqrt(
    x, name=None
)

Used in the notebooks

Used in the tutorials
x = tf.constant([[4.0], [16.0]]) 
tf.sqrt(x) 
<tf.Tensor: shape=(2, 1), dtype=float32, numpy= 
  array([[2.], 
         [4.]], dtype=float32)> 
y = tf.constant([[-4.0], [16.0]]) 
tf.sqrt(y) 
<tf.Tensor: shape=(2, 1), dtype=float32, numpy= 
  array([[nan], 
         [ 4.]], dtype=float32)> 
z = tf.constant([[-1.0], [16.0]], dtype=tf.complex128) 
tf.sqrt(z) 
<tf.Tensor: shape=(2, 1), dtype=complex128, numpy= 
  array([[0.0+1.j], 
         [4.0+0.j]])> 

Args:

  • x: A tf.Tensor of type bfloat16, half, float32, float64, complex64, complex128
  • name: A name for the operation (optional).

Returns:

A tf.Tensor of same size, type and sparsity as x.

If x is a SparseTensor, returns SparseTensor(x.indices, tf.math.sqrt(x.values, ...), x.dense_shape)