# YOLO object detection

**URL:** https://discourse.processing.org/t/yolo-object-detection/598
**Category:** Project Guidance
**Created:** [June 1, 2018, 1:21pm UTC](https://discourse.processing.org/t/yolo-object-detection/598 "2018-06-01T13:21:01Z")
**Posts on this page:** 4
**Page:** 1

<div class="post-metadata">

### Author: ![josephh](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.processing.org/josephh/32/210_2.png) [@josephh](https://discourse.processing.org/u/josephh)
#### Post date: [June 1, 2018, 1:21pm UTC](https://discourse.processing.org/t/yolo-object-detection/598/1 "2018-06-01T13:21:01Z")

</div>

Hello guys,

Is there a way to do YOLO real time object detection in processing (or P5.js/processing.py) using a library like this :

[![](https://img.youtube.com/vi/OQzrz6IwZGo/hqdefault.jpg "FPS 4K Darknet YOLO COCO with FPS") ](https://www.youtube.com/watch?v=OQzrz6IwZGo)

I already know OpenCV for computer vision but it doesn’t include object detection.

Thanks

---

<div class="post-metadata">

### Author: ![jeremydouglass](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.processing.org/jeremydouglass/32/20_2.png) [@jeremydouglass](https://discourse.processing.org/u/jeremydouglass)
#### Post date: [June 4, 2018, 12:51am UTC](https://discourse.processing.org/t/yolo-object-detection/598/2 "2018-06-04T00:51:54Z")

</div>

### Processing.py (Python mode:

Probably not. Processing.py runs on Jython, which means no C / Cython. So YOLO approaches like this:

> **[KleinYuan/easy-yolo](https://github.com/KleinYuan/easy-yolo)**
>
> Yolo (Real time object detection) model training tutorial with deep learning neural networks - KleinYuan/easy-yolo

…won’t work in Processing.py. Similarly, you [can’t run Tensorflow on Jython](https://stackoverflow.com/questions/45447797/import-tensorflow-in-a-jython-session?utm_medium=organic&utm_source=google_rich_qa&utm_campaign=google_rich_qa), so all related approaches to YOLO that do work on Processing 2.7 in general

- [https://github.com/thtrieu/darkflow/issues/350](https://github.com/thtrieu/darkflow/issues/350)

…won’t work on Processing.py.

### Processing (Java default mode):

For Java mode, if you want to do [Tensorflow in Processing](http://www.magicandlove.com/blog/2017/04/14/tensorflow-in-processing/)

- [http://www.magicandlove.com/blog/2017/04/14/tensorflow-in-processing/](http://www.magicandlove.com/blog/2017/04/14/tensorflow-in-processing/)

…then that setup might work with a Tensorflow-based YOLO detector:

> <https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/android/src/org/tensorflow/demo/TensorFlowYoloDetector.java>

### p5.js

I don’t know about p5.js, but I do know that recently @shiffman was working on some p5.js + [tensorflow.js](https://js.tensorflow.org/) example, so YOLO might work with that setup – but I’m not sure.

> **[shiffman/Tensorflow-JS-Examples](https://github.com/shiffman/Tensorflow-JS-Examples)**
>
> Working on some new examples with tensorflow.js and p5.js - shiffman/Tensorflow-JS-Examples

---

<div class="post-metadata">

### Author: ![josephh](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.processing.org/josephh/32/210_2.png) [@josephh](https://discourse.processing.org/u/josephh)
#### Post date: [June 4, 2018, 9:35am UTC](https://discourse.processing.org/t/yolo-object-detection/598/3 "2018-06-04T09:35:37Z")

</div>

Thanks for your answer 🙂

I checked the darknet YOLO object detection in Python/C :

- [https://github.com/thtrieu/darkflow](https://github.com/thtrieu/darkflow)

But I wasn’t able to get it work.  
Anyway I think that I’ll watch Daniel Shiffman’s videos on tensorFlow to learn.

By the way [https://github.com/KleinYuan/easy-yolo](https://github.com/KleinYuan/easy-yolo) won’t work on Windows, it requires Unbutu.

Thanks again & have a great day.

---

<div class="post-metadata">

### Author: ![jeremydouglass](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.processing.org/jeremydouglass/32/20_2.png) [@jeremydouglass](https://discourse.processing.org/u/jeremydouglass)
#### Post date: [June 4, 2018, 8:40pm UTC](https://discourse.processing.org/t/yolo-object-detection/598/4 "2018-06-04T20:40:13Z")

</div>

> [@josephh](#):
>
> I checked the darknet YOLO object detection in Python/C [… b]ut I wasn’t able to get it work.

Right. No C-based code of any kind will work in Processing.py, period.

Maybe also check out p5py, which is a separate Processing project under development and runs in native Python 3.