Install and run YOLOv4-Darknet on Windows (For GPU!)

preview_player
Показать описание
This video shows step by step tutorial on how to install and run yolov4-darknet on your local Windows system.

① ⚡⚡ Website Blog post on this ⚡⚡

⚡⚡ Medium post ⚡⚡

② ⚡⚡ Website Blog post on CUDA & cuDNN installation ⚡⚡

⚡⚡ Medium post on CUDA & cuDNN installation ⚡⚡

③ ⚡⚡ Github link for Official Darknet repository ⚡⚡

④ ⚡⚡ CUDA Toolkit download links ⚡⚡

⑤ ⚡⚡ Latest cuDNN version download ⚡⚡
⚡⚡ cuDNN archive download link ⚡⚡

⑥ ⚡⚡ OpenCV download link ⚡⚡

⑦ ⚡⚡ CUDA compiler Compute Capability(CC) link ⚡⚡

⑧⚡⚡Official yolov4 weights file ⚡⚡

⑨ ⚡⚡ Required Software ⚡⚡

#yolov4 #objectdetection #yolov4onwindows #yolov4darknet
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Making these videos takes a lot of time and effort, so if you like these videos and if you can, then please support the channel using any of the following:

► Buy me a coffee! ☕

► Support channel on Patreon! 🖖


▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Thanks for watching!
Рекомендации по теме
Комментарии
Автор

2 years later I can confirm the instructions still work, even when using CUDA 12.4. I've spent a week trying to get this set up, but this is the only method that's worked for me on windows 11. Thanks!

SeanGrech
Автор

Really good tutorial!

Guys, is important to follow all the steps and check the notes in order to acomplish what he got here, the PATH are extremelly important step, both, not only the CUDA and CUDNN but also adding the routes to the PATH variable.

I just tested it with a RTX 3060 - CUDA 11.4 and CUDNN 8.2 and worked

December 18.12.2022

StaMariaRock
Автор

Guyss if you find this channel, then you have found a gem.. What a tutorial... i was watching this video now which is after 1 year of him uploading this video and i had some errors and for him this was 1 year old video but he was still replying to my comments.. and he helped me to solve my errors for solving my errors i spent hours but he helped me find a solution...

romesh
Автор

Thank you very much sir. This tutorial is very helpful. Finally, I successfully installed Darknet after following this tutorial :)) Previously, I almost gave up.

MonicaWidiasri_
Автор

lifesaver! The installed bugged me for a whole day before I saw this video. Thank you soooo much!!!

lizhang
Автор

Thanks for your for the detailed explanation. I am working now with darknet on my notebook without any problem.

agustingarcia
Автор

Thank you for the detailed demonstration. I succeed in implementing it on Windows. : )

alexanderyang
Автор

Awesome, i had some issues setting up environmental variables. Thanks for sharing your knowledge.

j_ar
Автор

Thank helped me a I can run yolov4 on my windows

abdullahsafwan
Автор

Really tks you!!
I have tried 3 times to work. It's fine.
The PATH extremely important step. Remember, restart PC

nthinh
Автор

Sir kindly make more videos please using model trainings on pytorch and many more.Your content and your way of explaining through your blogs and your channel is amazing🔥.

abubakarsaleem
Автор

Sir, I followed all your steps but at the final step of image detection cmd shows "CUDA error: CUDA driver version is insufficient for CUDA runtime version", my CUDA version is 11.0, cudnn 8.0.5 and opencv 4.5.1 ... kindly help me

ZakaUrRehman-kwgk
Автор

The best so far on this. Thank you

Error I had:

CMake Error at CMakeLists.txt:156 (message):
CUDA not found, please build explicitly with -DENABLE_CUDA=OFF if you do
not want CUDA.

mohammadyahya
Автор

Hi sir, I have a issue "The source directory "D:/darknet" does not appear to contain CMakeLists.txt." How can I fix this ?

dungao
Автор

Hi, I got error: nvcuda.dll not found. Please help me

marsmemes
Автор

After giving cmd the command to use detector.exe to output the dog image. My computer says it cannot locate the file "zlibwapi.dll", so I looked up on Google.
In Nvidia's guide documentation about cuDNN, it mentioned in 3.1.3 that "installing zlib" and then add it to the system variable PATH.
After done this procedure, I managed to output the done image.

This is a reference for friends met same problem as me, hope to help you too. : )

alexanderyang
Автор

Sir when i generate Cmake my cuda compiler not found, im sure i installed the cuda and cudnn like the video

Necode
Автор

Hi, when I select " configure " in cmake, i get cmake error: CUDA not found, please build explicitly with -DENABLE_CUDA=OFF if you do
not want CUDA. i don't know what to do. thanks

nguyenanhquan
Автор

Hello sir, followed all your steps...am at the final step of image detection but cmd shows "CUDA error: CUDA driver version is insufficient for CUDA runtime version" ...my CUDA version is 11.5 ... kindly help sir!

mithun
Автор

thanks it helped me a lot, I have a question is there any way to run yolo in a python gui on windows 10? thanks!!

viche