Skip to main content
Crowdfunding
Python + AI for Geeks
Practice

Tensor Dimensions

Tensor Dimensions​

A tensor's rank indicates the number of axes it contains, and the size of each dimension represents the length along that axis.


0-D Tensor (Scalar)​

This is a single number or a lone value.

Example of a 0-D Tensor (Scalar)
import tensorflow as tf
scalar = tf.constant(3.14)
print(scalar)

1-D Tensor (Vector)​

An array of numbers, similar to a list in Python.

Example of a 1-D Tensor (Vector)
vector = tf.constant([1, 2, 3])
print(vector)

2-D Tensor (Matrix)​

A structured dataset made up of rows and columns.

Example of a 2-D Tensor (Matrix)
matrix = tf.constant([[1, 2], [3, 4], [5, 6]])
print(matrix)

3-D and Higher-Dimensional Tensors​

Used to represent more complex structures, such as images and video data.

Example of a 3-D Tensor
tensor_3d = tf.constant([[[1, 2], [3, 4]], [[5, 6], [7, 8]]])
print(tensor_3d)

Properties of a Tensor​

Tensors have several properties:

  • shape: A tuple representing the dimensions of the tensor.

  • dtype: The data type stored in the tensor (e.g., float32, int32).

  • device: Information about the device (CPU/GPU) where the tensor is executed.

Checking Tensor Properties
example_tensor = tf.constant([[1, 2, 3], [4, 5, 6]], dtype=tf.float32)

print(f"Shape: {example_tensor.shape}")
# Shape: (2, 3)

print(f"Data Type: {example_tensor.dtype}")
# Data Type: <dtype: 'float32'>

By examining the properties of a tensor, you can easily determine its structure and data type.

In the next lesson, we'll go over a brief quiz to review what we have learned so far.

Want to learn more?

Join CodeFriends Plus membership or enroll in a course to start your journey.