Python – tensorflow.math.floor()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning neural networks. floor() is used to find the element wise floor value of the input i.e. the largest integer not greater than x

Syntax: tensorflow.math.floor( x, name)

Parameters:

•  x: It’s a tensor and allowed dtype for this tensor are  bfloat16, half, float32, float64.
• name: It’s an optional argument that defines the name for the operation.

Returns: It returns a tensor of same dtype as x.

Example 1:

Python3

# importing the library
import tensorflow as tf

# initializing the input
a = tf.constant([1.5, 2.7, 3.9, 1.2, 1.8], dtype = tf.float64)

# printing the input
print('a: ',a)

# Finding the floor value
r = tf.math.floor(a)

# printing the result
print("Result: ",r)

Output:

a:  tf.Tensor([1.5 2.7 3.9 1.2 1.8], shape=(5,), dtype=float64)
Result:  tf.Tensor([1. 2. 3. 1. 1.], shape=(5,), dtype=float64))

Example 2: In this example 2-D tensor is used.

Python3

# importing the library
import tensorflow as tf

# initializing the input
a = tf.constant([[1.5, 2.7], [3.9, 1.2]], dtype = tf.float64)

# printing the input
print('a: ',a)

# Finding the floor value
r = tf.math.floor(a)

# printing the result
print('Result: ',r)

Output:

a:  tf.Tensor(
[[1.5 2.7]
 [3.9 1.2]], shape=(2, 2), dtype=float64)
Result:  tf.Tensor(
[[1. 2.]
 [3. 1.]], shape=(2, 2), dtype=float64)

Example 3: In this example invalid dtype tensor is used. It will raise NotFoundError.

Python3

# importing the library
import tensorflow as tf

# initializing the input
a = tf.constant([1.5, 2.7, 3.9, 1.2, 1.8], dtype = tf.complex128)

# printing the input
print('a: ',a)

# Finding the floor value
r = tf.math.floor(a)

Output:

a:  tf.Tensor([1.5+0.j 2.7+0.j 3.9+0.j 1.2+0.j 1.8+0.j], shape=(5,), dtype=complex128)

---------------------------------------------------------------------------

NotFoundError                             Traceback (most recent call last)

 in ()
      6 
      7 # Finding the floor value
----> 8 r = tf.math.floor(a)

2 frames

/usr/local/lib/python3.6/dist-packages/six.py in raise_from(value, from_value)

NotFoundError: Could not find valid device for node.
Node:{{node Floor}}
All kernels registered for op Floor :
  device='XLA_GPU'; T in [DT_FLOAT, DT_DOUBLE, DT_BFLOAT16, DT_HALF]
  device='XLA_CPU'; T in [DT_FLOAT, DT_DOUBLE, DT_BFLOAT16, DT_HALF]
  device='XLA_CPU_JIT'; T in [DT_FLOAT, DT_DOUBLE, DT_BFLOAT16, DT_HALF]
  device='XLA_GPU_JIT'; T in [DT_FLOAT, DT_DOUBLE, DT_BFLOAT16, DT_HALF]
  device='GPU'; T in [DT_DOUBLE]
  device='GPU'; T in [DT_HALF]
  device='GPU'; T in [DT_FLOAT]
  device='CPU'; T in [DT_DOUBLE]
  device='CPU'; T in [DT_HALF]
  device='CPU'; T in [DT_FLOAT]
 [Op:Floor]