Learn practical skills, build real-world projects, and advance your career
Updated 3 years ago
Building a YOLOv3 Object Detector with Darknet in the Cloud! (GPU ENABLED)
This tutorial will help you build YOLOv3 easily in the cloud with GPU enabled so that you can run real-time object detections as well as train your very own custom object detector!
!pip install jovian --upgrade
import jovian
jovian.commit(environment=None)
[jovian] Attempting to save notebook..
# clone darknet repo
!git clone https://github.com/AlexeyAB/darknet
Cloning into 'darknet'...
remote: Enumerating objects: 36, done.
remote: Counting objects: 100% (36/36), done.
remote: Compressing objects: 100% (26/26), done.
remote: Total 14558 (delta 13), reused 19 (delta 8), pack-reused 14522
Receiving objects: 100% (14558/14558), 13.26 MiB | 23.40 MiB/s, done.
Resolving deltas: 100% (9894/9894), done.
# change makefile to have GPU and OPENCV enabled
%cd darknet
!sed -i 's/OPENCV=0/OPENCV=1/' Makefile
!sed -i 's/GPU=0/GPU=1/' Makefile
!sed -i 's/CUDNN=0/CUDNN=1/' Makefile
/content/darknet