# Yolo algorithm - anchor box vs classes

**URL:** <https://community.deeplearning.ai/t/yolo-algorithm-anchor-box-vs-classes/77417>\
**Category:** Convolutional Neural Networks\
**Tags:** coursera-platform\
**Created:** [December 21, 2021, 2:11pm UTC](https://community.deeplearning.ai/t/yolo-algorithm-anchor-box-vs-classes/77417 "2021-12-21T14:11:21Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![ai\_curious](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/ai_curious/32/128003_2.png) [@ai\_curious](https://community.deeplearning.ai/u/ai_curious)\
**Post date:** [December 21, 2021, 3:53pm UTC](https://community.deeplearning.ai/t/yolo-algorithm-anchor-box-vs-classes/77417/2 "2021-12-21T15:53:30Z")

</div>

> [@sagi\_levi](#):
>
> we choose every anchor box in the shape of every class

This is not correct. Anchor boxes are based on object shapes only…nothing to do with object type. There are several threads discussing this already in the forum. You can find them with search…

[[https://community.deeplearning.ai/search?q=Anchor%20boxes](https://community.deeplearning.ai/search?q=Anchor%20boxes)]

This is one of the threads returned by that search that might be helpful…. [Number of anchor boxes](https://community.deeplearning.ai/t/number-of-anchor-boxes/68657)

---

_[View the full topic](https://community.deeplearning.ai/t/yolo-algorithm-anchor-box-vs-classes/77417)._