What is a Tensor?

Tensorflow's name is directly derived from its core framework: Tensor. In Tensorflow, all the computations involve tensors. A tensor is a vector or matrix of n-dimensions that represents all types of data. All values in a tensor hold identical data type with a known (or partially known) shape. The shape of the data is the dimensionality of the matrix or array.

A tensor can be originated from the input data or the result of a computation. In TensorFlow, all the operations are conducted inside a graph. The graph is a set of computation that takes place successively. Each operation is called an op node and are connected to each other.

The graph outlines the ops and connections between the nodes. However, it does not display the values. The edge of the nodes is the tensor, i.e., a way to populate the operation with data.

In Machine Learning, models are feed with a list of objects called feature vectors. A feature vector can be of any data type. The feature vector will usually be the primary input to populate a tensor. These values will flow into an op node through the tensor and the result of this operation/computation will create a new tensor which in turn will be used in a new operation. All these operations can be viewed in the graph.

Representation of a Tensor

In TensorFlow, a tensor is a collection of feature vectors (i.e., array) of n-dimensions. For instance, if we have a 2x3 matrix with values from 1 to 6, we write:

TensorFlow represents this matrix as:

[[1, 2, 3], 
   [4, 5, 6]]                                           

If we create a three-dimensional matrix with values from 1 to 8, we have:

TensorFlow represents this matrix as:

[ [[1, 2],  
       [[3, 4],  
       [[5, 6],  
       [[7,8] ]                                          

Note: A tensor can be represented with a scalar or can have a shape of more than three dimensions. It is just more complicated to visualize higher dimension level.

Types of Tensor

In TensorFlow, all the computations pass through one or more tensors. A tensor is an object with three properties:

• A unique label (name)
• A dimension (shape)
• A data type (dtype)

Each operation you will do with TensorFlow involves the manipulation of a tensor. There are four main tensors you can create:

• tf.Variable
• tf.constant
• tf.placeholder
• tf.SparseTensor

In this tutorial, you will learn how to create a tf.constant and a tf.Variable.

Before we go through the tutorial, make sure you activate the conda environment with TensorFlow. We named this environment hello-tf.

For MacOS user:

source activate hello-tf                                     

For Windows user:

activate hello-tf                                   

After you have done that, you are ready to import tensorflow

# Import tf
import tensorflow as tf                                     

Create a tensor of n-dimension

You begin with the creation of a tensor with one dimension, namely a scalar.

To create a tensor, you can use tf.constant()

tf.constant(value, dtype, name = "")
arguments
 
- `value`: Value of n dimension to define the tensor. Optional
- `dtype`: Define the type of data:    
    - `tf.string`: String variable    
    - `tf.float32`: Flot variable    
    - `tf.int16`: Integer variable
- "name": Name of the tensor. Optional. By default, `Const_1:0`                                              

To create a tensor of dimension 0, run the following code

## rank 0
# Default name
r1 = tf.constant(1, tf.int16) 
print(r1)                                              

Output

Tensor("Const:0", shape=(), dtype=int16)