# Reduction and Comparison

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

## We'll cover the following

## 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**.

Function Name | Purpose |
---|---|

mean | Get the mean value of the tensor in the given dimension. |

sum | Sum the values of the tensor over the given dimension. |

median | Get the median value of tensor in the given dimension. |

std | Compute the standard deviation of the tensor over the given dimension. |

prod | Product the values of the tensor over the given dimension. |

cumsum | Cumulative sum of values of the tensor over the given dimension. |

Get hands-on with 1400+ tech skills courses.