Natural Language Processing with TensorFlow/

...

/

Defining Operations in TensorFlow

Defining Operations in TensorFlow

Learn about the different operations in TensorFlow.

We'll cover the following...

An operation in TensorFlow takes one or more inputs and produces one or more outputs. If we take a look at the TensorFlow API, we’ll see that TensorFlow has a massive collection of operations available. Here, we’ll take a look at a selected few of the myriad TensorFlow operations.

Comparison operations

Comparison operations are useful for comparing two tensors. The following code example includes a few useful comparison operations.

To understand the working of these operations, let’s consider two example tensors, x and y:

Python 3.10.4
# Let's assume the following values for x and y 
# x (2-D tensor) => [[1,2],[3,4]]
# y (2-D tensor) => [[4,3],[3,2]]
x = tf.constant([[1, 2], [3, 4]], dtype = tf.int32) 
y = tf.constant([[4, 3], [3, 2]], dtype = tf.int32)
# Checks if two tensors are equal element-wise and returns a boolean tensor
# x_equal_y => [[False,False],[True,False]]
x_equal_y = tf.equal(x, y, name = None)
# Checks if x is less than y element-wise and returns a boolean tensor 
# x_less_y => [[True,True],[False,False]]
x_less_y = tf.less(x, y, name = None)
# Checks if x is greater or equal than y element-wise and 
#returns a boolean tensor
# x_great_equal_y => [[False,False],[True,True]]
x_great_equal_y = tf.greater_equal(x, y, name = None)
# Selects elements from x and y depending on whether, 
#the condition is satisfied (select elements from x) 
#or the condition failed (select elements from y)
condition = tf.constant([[True, False], [True, False]], dtype = tf.bool)
# x_cond_y => [[1,3],[3,2]]
x_cond_y = tf.where(condition, x, y, name = None)
print('Is X == Y (element-wise)?')
print(x_equal_y.numpy())
print('\nIs X < Y (element-wise)?')
print(x_less_y.numpy())
print('\nIs X >= Y (element-wise)?')
print(x_great_equal_y.numpy())
print('\nX or Y depending on the condition (element-wise)')
print(x_cond_y.numpy())

We have two tensors, x and y, in the code above, which we used to compare element-wise. First, we check if these are equal or not (line 9), then we check if x is less than y (line 13), and finally, if x is greater than or equal to y (line 17). We select elements from tensors x and y based on the corresponding elements of the boolean tensor condition. If the condition is True, it selects the element from x; otherwise, it selects the element from y (lines 20–23).

In the figure below, we show the symbols of the comparison operators:

Comparison operators
Comparison operators

Mathematical operations

TensorFlow allows us to perform math ...