Python - tensorflow.fill()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning  neural networks. 

fill() is used to generate a tensor having scalar value.

Syntax: tensorflow.fill( dims, value, name)

Parameters:

• dims: It is 1-D sequence of dtype int32 or int64 with non-negative integers representing the shape of the resulting Tensor.
• value:  It is the value to be filled.
• name(optional):  It defines the name of the operation. 

Returns: It returns a Tensor of shape dim.

Raises:

• InvalidArgumentError: This error is raised when dim contains negative values.
• NotFoundError: This error is raised when dim contains non-integer values.

Example 1:

# Importing the library
import tensorflow as tf

# Initializing the input
dim = [4, 5]
value = 5

# Printing the input
print('dim: ', dim)
print('value: ', value)

# Calculating result
res = tf.fill(dim, value)

# Printing the result
print('res: ', res)

Output:

dim:  [4, 5]
value:  5
res:  tf.Tensor(
[[5 5 5 5 5]
 [5 5 5 5 5]
 [5 5 5 5 5]
 [5 5 5 5 5]], shape=(4, 5), dtype=int32)

Example 2:

# Importing the library
import tensorflow as tf

# Initializing the input
dim = [4, 2, 5]
value = 5

# Printing the input
print('dim: ', dim)
print('value: ', value)

# Calculating result
res = tf.fill(dim, value)

# Printing the result
print('res: ', res)

Output:

dim:  [4, 2, 5]
value:  5
res:  tf.Tensor(
[[[5 5 5 5 5]
  [5 5 5 5 5]]

 [[5 5 5 5 5]
  [5 5 5 5 5]]

 [[5 5 5 5 5]
  [5 5 5 5 5]]

 [[5 5 5 5 5]
  [5 5 5 5 5]]], shape=(4, 2, 5), dtype=int32)

aman neekhara

Follow

Improve

Article Tags :

• Python
• Tensorflow
• Python-Tensorflow

Practice Tags :

• python