YOLOv4 Custom Object Detection Tutorial: Part 2 (Training YOLOv4 Darknet on Custom Dataset)

Train YOLOV4 custom object detector using darknet. This second part of the tutorial explains steps to train a custom object detection model using YOLOv4 darknet on our own custom dataset. We will also run the trained YOLOv4 custom object detector on images and videos. I only focus on training custom YOLOv4 but you can easily adapt this tutorial for training tiny custom YOLOv4 object detector.

To train YOLOv4 to detect a custom object, I chose "John Wick" as an example. You can choose any object of your preference.

**Labeled Dataset and trained model is available for our Patreon supporters.**

Link to Part 1:
---------------------------------------------
► Time Stamps:
Introduction: (0:00)
Configuring Darknet YOLOv4 : (0:24)
Training Darknet YOLOv4: (7:27)
Resuming Training: (9:32)
Custom Object Detection on Videos: (10:16)
Custom Object Detection on Images: (11:47)
---------------------------------------------

Links to repositories used in the video:

Build YOLOv4 Darknet on Windows 10:

Building OpenCV with GPU support:

►Commands
Training:
Custom Object Detection on Webcam:
Custom Object Detection on Video:
Custom Object Detection on Images:

#TheCodingBug
#YOLOv4
#Darknet
---------------------------------------------
► My Other Tutorials:
---------------------------------------------
---------------------------------------------
DISCLAIMER: Links included in this description might be affiliate links. If you purchase a product or service with the links that I provide I may receive a small commission. There is no additional charge to you!

[Plexify-vs]

thanks god, someone did a tutorial without using google collab

Ty so much

[viraldoshi]

This is the tutorial ever... believe me i have seen more than 20 channels implement this... but if u have landed here this is the bessttt Yolo application on custom dataset video till now... Kudos bruhh

[TheCodingBug]

Link to Part 1:

Build YOLOv4 Darknet on Windows 10:

Building OpenCV 4.4.0 with GPU from source:

[likeyou]

I have gtx 1060 3gb, and this setup causes Error: cuDNN isn't found FWD algo for convolution.
I saw in my task manager that it means that i'm out of memory, so I changed width=320, height=320, batches=64, subdivisions=64 and it worked!

[hamzakarim]

Thank you For all your tutorials. You have the best tutorial out of all Yolo tutorials out there!

[danilocarusoweb]

sorry I'm new I can't find the darkne.exe file... did I skip any steps?

[richtankone]

Awesome work!! I've tried multiple times to get some form of custom object detection up and running. Not until your tutorial have I succeeded! Subscribed and liked!

[inari]

thank you.
This tutorial really helps me a lot.

[chandank]

Great video! only a small question - how to stop the training?

[nugratasik]

great tutorial! thank you so muchh.. but can I set the line_thickness to some spesific size? thankyou..

[malikbilal]

When I start Training I got this error, Why it is how to solve this.
Error: cuDNN isn't found FWD algo for convolution.

[dsdummyaccount]

@The Coding bug, Its a great tutorial . I have question that if weights is trained for 2 classes and wanted to add another 2 classes to the existing weights .is it possible ?? .should training start from the scratch ?

[sefadogan]

I am getting an error at 8:40 . Last 5 lines of whole error is:
Wrong annotation: class_id = 29. But class_id should be [from 0 to 0], file: data/obj/john wick_30.txt

Wrong annotation: class_id = 12. But class_id should be [from 0 to 0], file: data/obj/john wick_13.txt

Wrong annotation: class_id = 9. But class_id should be [from 0 to 0], file: data/obj/john wick_10.txt

Wrong annotation: class_id = 23. But class_id should be [from 0 to 0], file: data/obj/john wick_24.txt
Error: cuDNN isn't found FWD algo for convolution.

I am getting a lot of errors/warning that titled "Wrong annotation:"so ı am stuck at this stage. What should i do?

My english is not good. I hope i could explain myself. I am sorry for my english

[ishac]

Can you also make a video on counting objects ?

[riteshananth]

How to add an extra class ( for ex : Auto Rickshaw ) to the existing 80 classes from the Coco Dataset. I felt that your explanation was lucid and i would be thankful if you could give a solution to this problem.

[hikarinakamura]

i get an error "Error: cuDNN isn't found FWD algo for convolution." when training data. any way to solve this?

[aitharajusaihemanth]

Can we run this on a youtube video instead of a video from our local repository ?

[khazinahasan]

Thanks alot for such amazing and helpful tutorial.
I am training for "person" but when i train, i am getting IOU=0.000, i dont know where is the problem or how much IOU threshold I need to set?

[alexahavounson]

I love your tutorials! but What will be the max_batch size if I labeled 25000 images and have 1 class? Please help me!

[sefadogan]

How can i take accuracy percentage value from command prompt to use in my code?