YOLOv3 Object Detection with Darknet for Windows/Linux | Install and Run with GPU and OPENCV
Why Stack Overflow recommends it
Stack Overflow users link it as a walkthrough for setting up Darknet and YOLO, both as a tutorial to follow and as a reference when troubleshooting CUDA and CMake setup problems.
Recommended by 1 people across 1 different months, 2021 to 2023.
What it is
A 26-minute step-by-step tutorial from The AI Guy on installing and building YOLOv3 with Darknet on Windows and Linux, with GPU and OpenCV support enabled. It also covers checking whether your machine has a GPU and running detections on images and videos.
What people said
Recommends Serge de Gosson de Varennes · 2021-11 · Stack Overflow · on “YOLO v4 environment building”
I watched the video you linked to. Good but lacks some steps (my Chinese is limited so I might have misunderstood things). Look at this video [this video]
Cites AK_KA · 2021-04 · Stack Overflow · on “Installing Darknet on Windows 10 without OpenCV and CUDA (no GPU on own device): issues”
I have been trying to install Darknet on my own device (which runs on Windows 10) unsuccessfully. I am following the rough guide here: [LINK] . However, it only contains the steps for a Linux configuration, so I have been checking out posts and videos about doing it on Windows. Has anyone come across a relatively straightforward guide or YouTube video about how to install Darknet without the need to have a local GPU (as a dependency, CUDA requires GPU) that you have found particularly useful? I have been following a few ( [this video] was pretty clear), but they all go through the CUDA installation as a must (where CUDA should be an optional dependency). Many thanks in advance!
Cites Jan · 2023-01 · Stack Overflow · on “GPU support error in cmake while configuring the darknet for YOLOv3 and YOLOv4”
I've been trying to set up the YOLOv3 with the darknet (according to this tutorial: [this video] at 11:30). While configuring the darknet with CUDA support, CMake raised CMake Error at CMakeLists.txt:156 (message): CUDA not found, please build explicitly with -DENABLE_CUDA=OFF if you do not want CUDA. [LINK] I looked at a bunch of GitHub and StackOverflow threads about this or any similar error message, but I haven't found any solution yet that works. By the way, when I check my CUDA version (11.2) in cmd (I'm on Windows), the version shows up correctly.