# How to convert TensorFlow to one hot | One hot encoding TensorFlow example

Do you know how to convert TensorFlow to one hot? Let us discuss and understand how the TensorFlow tensor will be transformed into one hot. And also we are going to cover one hot encoding TensorFlow example.

• Convert to one hot TensorFlow
• How to Convert one hot to integer TensorFlow.
• One hot encoding TensorFlow example
• Convert tensor to list TensorFlow
• Convert tensor to int TensorFlow

## Convert to one hot tensorflow

• Here we will discuss converting the input tensor to one hot in TensorFlow.
• One hot encoding is the crucial process of transforming the variables in categorical data fed into the machine and deep learning algorithms, improving predictions and model classification accuracy.
• In one-hot encoding, binary variables (or, to be more precise, vectors) in place of category variables, which can only take a value of 0 or 1.
• Essentially, we’re stating whether or not a specific item of a specific category was present. For each data entry and the columns that reflect their classifications, new rows are created. 1s and 0s are used to indicate their presence or absence.

Syntax:

Let’s have a look at the Syntax and understand the working of the tf.one_hot() function in Python TensorFlow

``````tf.one_hot(
indices,
depth,
on_value=None,
off_value=None,
axis=None,
dtype=None,
name=None
)``````
• It consists of a few parameters
• indices: This parameter defines the tensor of indices.
• depth: a scalar indicating the hot dimension’s depth.
• on_value: By default, it takes none value a scalar specifying the output value to use when indices[j] = i.
• off_value: By default, it takes none value a scalar specifying the output value to use when indices[j] = i.
• axis: This parameter defines the axis to fill the inner and outer parts.
• dtype: By default, it takes none value and it specifies the data type of the output tensor.
• name: This parameter specifies the name of the operation and by default, it takes none value.

Example:

``````import tensorflow as tf

indices_value = [15, 28, 9,13]
new_val = 5
new_output=tf.one_hot(indices_value, new_val)
print(new_output)``````

In the above code we have imported the TensorFlow library and then initialize a list in which we have assigned the indices numbers.

After that, we used the tf.one_hot() function and within this function, we passed the indices and depth as an argument. It will return the shape of the list and indices.

Here is the Screenshot of the following given code

This is how to convert the tensor to one hot in TensorFlow.

## How to Convert one hot to integer TensorFlow

• In this section, we will discuss how to convert one hot to an integer tensor in Tensorflow.
• To perform this particular task we are going to use the tf.argmax() function and it will return the index of the largest element in a tensor’s set of elements. It may be possible to return an index of the maximum values across rows and columns if the tensor is two-dimensional.

Syntax:

Here is the Syntax of tf.argmax() function in Python TensorFlow

``````tf.math.argmax(
input,
axis=None,
output_type=tf.dtypes.int64,
name=None
)``````
• It consists of a few parameters
• input: This parameter defines the input tensor.
• axis: By default, it is 0 and it is an integer the axis which we want to reduce.
• output_type: By default it takes tf.dtypes.int64() and it is an optional datatype.
• name: This parameter specifies the name of the operation and by default, it takes none value.

Example:

``````import tensorflow as tf
tf.compat.v1.disable_eager_execution()
number_of_batch = 3
number_of_shape = 4
encoded_tensor = tf.constant([[1, 0, 1, 0],
[0, 1, 0, 0],
[0, 0, 0, 1]])

result = tf.argmax(encoded_tensor, axis=1)

with tf.compat.v1.Session() as val:
new_output=val.run(result)
print(new_output)``````

First, we created an one_hot tensor with batch size and classes in the following given code. Next, we used the tf.argmax() function and assign the encoded tensor along with the axis. It will return the index of the largest element in a tensor’s set of elements.

Here is the implementation of the following given code

As you can see in the Screenshot we have transformed one hot to an integer in TensorFlow.

## One hot encoding tensorflow example

• Let us discuss how to use the one-hot encoding function in Python TensorFlow.
• To do this task, we are going to use the tf.one_hot() function and it will convert the random number with binary integer numbers.
• In this example we have create the session by importing the tf.compat.v1.disable_eager_execution() function.
• Next, we will declare the indices numbers in the list and then we are going to use the tf.one_hot() function and assign the indices, and depth axis as an argument.

Example:

``````import tensorflow as tf
tf.compat.v1.disable_eager_execution()
indices_val = [1,8,2,3,1]
input_tensor = tf.constant(4)

result = tf.one_hot(indices_val, input_tensor,on_value=1.0,off_value=0.0, axis =-1)
with tf.compat.v1.Session() as val:
new_output=val.run(result)
print(new_output)``````

You can refer to the below Screenshot

## Convert tensor to list tensorflow

• In this section, we will discuss how to convert the tensor to a list in Python TensorFlow.
• In this example, we are going to use the tf.compat.v1.disable_eager_execution() for running the session. To convert the tensor into a list first we will import the eager_execution function along with the TensorFlow library.
• Next, we will create the constant values by using the tf.constant() function and, then we are going to run the session by using the syntax session=tf.compat.v1.Session() in eval() function.

Example:

``````import tensorflow as tf
tf.compat.v1.disable_eager_execution()
new_val = tf.constant([[178,267,189],[34,20,189]])
new_result = new_val.eval(session=tf.compat.v1.Session()).tolist()
new_result``````

Here is the execution of the following given code

This is how to convert the tensor to a Python list in TensorFlow

## Convert tensor to int tensorflow

• In this section, we will discuss how to convert the tensor to an integer in Python TensorFlow.
• To do this task we are going to use the tf.cast() function and this function is used to convert the input datatype to a different datatype.
• For example, you have created an input tensor and assigned the elements in the order of floating points and now you want to convert the floating point to decimal. For this, we are going to use the tf.cast() function.

Example:

``````import tensorflow as tf
# Creation of tensor by using the tf.constant() function
input_tensor = tf.constant([16.98, 23.2], dtype=tf.float32)
result=tf.cast(input_tensor, tf.int32)
# Display the Content
print(result)``````

Here is the implementation of the following given code

As you can see in the Screenshot we have converted the tensor to an integer in TensorFlow.

In this article, we have discussed how to convert TensorFlow to one hot. Let us discuss and understand how the tensorflow tensor will be transformed into one hot. And also we have covered the following given topics.

• Convert to one hot tensorflow
• How to Convert one hot to integer tensorflow.
• One hot encoding tensorflow example
• Convert tensor to list tensorflow
• Convert tensor to int tensorflow

You may also like the following Tensorflow tutorials: