Python - tensorflow.math.cumsum()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning  neural networks. cumsum() is used to calculate the cumulative sum of input tensor.

Syntax: tensorflow.math.cumsum(x, axis, exclusive, reverse, name)

Parameters: 

• x: It's the input tensor. Allowed dtype for this tensor are  float32, float64, int64, int32, uint8, uint16, int16, int8, complex64, complex128, qint8, quint8, qint32, half.
• axis(optional): It's a tensor of type int32. It's value should  be in the range  A Tensor of type int32 (default: 0). Must be in the range [-rank(x), rank(x)).  Default value is 0.
• exclusive(optional): It's of type bool. Default value is False and if set to true then the output for input [a, b, c] will be [0, a, a+b].
• reverse(optional): It's of type bool. Default value is False and if set to true then the output for input [a, b, c] will be [a+b+c, a+b, a].
• name(optional): It defines the name for the operation.

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

Example 1:

# importing the library
import tensorflow as tf

# initializing the input
a = tf.constant([1, 2, 4, 5], dtype = tf.int32)  

# Printing the input
print("Input: ",a)

# Cumulative sum
res  = tf.math.cumsum(a)

# Printing the result
print("Output: ",res)

Output:

Input:  tf.Tensor([1 2 4 5], shape=(4,), dtype=int32)
Output:  tf.Tensor([ 1  3  7 12], shape=(4,), dtype=int32)

Example 2: In this example both reverse and exclusive are set to True.

# importing the library
import tensorflow as tf

# initializing the input
a = tf.constant([2, 3, 4, 5], dtype = tf.int32)  

# Printing the input
print("Input: ",a)

# Cumulative sum
res  = tf.math.cumsum(a, reverse = True, exclusive = True)

# Printing the result
print("Output: ",res)

Output: 

Input:  tf.Tensor([2 3 4 5], shape=(4,), dtype=int32)
Output:  tf.Tensor([12  9  5  0], shape=(4,), dtype=int32)