This course teaches you how to create, manipulate, and understand tensors for machine learning using PyTorch.

Manipulate Tensor in PyTorch (Mini Course)_468 x 60.png

pytorch.tar.gz

pytorch

Tensors form the fundamental building block of the PyTorch ecosystem. Various components, such as network layers, loss function, gradient descent, and optimizer rely on underlying tensor operations.

In this course, you will get a comprehensive overview of tensors starting with how to create one. You will learn the many different types of tensors as well as how to concatenate and manipulate them by selecting elements, changing the shape, and more.

By the end of this course, you will have a basic understanding of how to work with PyTorch tensors and what they allow you to do.

Basic Pytorch Tensor Manipulation for Machine Learning

# Reduction functions

The reduction operator is a type of operator that is commonly used in parallel programming to reduce the elements of an array into a single result. For example, we can calculate the mean value of a float array is a reduction operation.

`PyTorch` provides some useful functions for reduction. If you have used NumPy before, you may notice the usage and name are the same. Below are some important functions, they all have a parameter `dim`, which indicates on which dimension the summarization is performed. The default value for `dim` is **0**.






<table style="width:90%">
  <tr>
    <th style="width:20%">Function Name</th>
    <th style="text-align: center">Purpose</th>
    
  </tr>
  <tr>
    <td>mean</td>
    <td style="text-align: left">Get the mean value of the tensor in the given dimension.</td>
  </tr>
<tr>
    <td>sum</td>
    <td style="text-align: left">Sum the values of the tensor over the given dimension.</td>
  </tr>
<tr>
    <td>median</td>
    <td style="text-align: left">Get the median value of tensor in the given dimension.</td>
  </tr>
<tr>
    <td>std</td>
    <td style="text-align: left">Compute the standard deviation of the tensor over the given dimension.</td>
  </tr>
<tr>
    <td>prod</td>
    <td style="text-align: left">Product the values of the tensor over the given dimension.</td>
  </tr>
<tr>
    <td>cumsum</td>
    <td style="text-align: left">Cumulative sum of values of the tensor over the given dimension.</td>
  </tr>
  
</table>


# Reduction functions

The reduction operator is a type of operator that is commonly used in parallel programming to reduce the elements of an array into a single result. For example, we can calculate the mean value of a float array is a reduction operation.

`PyTorch` provides some useful functions for reduction. If you have used NumPy before, you may notice the usage and name are the same. Below are some important functions, they all have a parameter `dim`, which indicates on which dimension the summarization is performed. The default value for `dim` is **0**.






<table>
  <tr>
    <th>Function Name</th>
    <th>Purpose</th>
    
  </tr>
  <tr>
    <td>mean</td>
    <td>Get the mean value of the tensor in the given dimension.</td>
  </tr>
<tr>
    <td>sum</td>
    <td>Sum the values of the tensor over the given dimension.</td>
  </tr>
<tr>
    <td>median</td>
    <td>Get the median value of tensor in the given dimension.</td>
  </tr>
<tr>
    <td>std</td>
    <td>Compute the standard deviation of the tensor over the given dimension.</td>
  </tr>
<tr>
    <td>prod</td>
    <td>Product the values of the tensor over the given dimension.</td>
  </tr>
<tr>
    <td>cumsum</td>
    <td>Cumulative sum of values of the tensor over the given dimension.</td>
  </tr>
  
</table>


In this lesson, we will look at some reduction and comparison operations.

__default

Reduction and Comparison

Reduction functions