Skip to content

a simple notebook that allows for easy experimentation with the YOLOv5 object detection algorithm and YouTube Bounding Box dataset

License

Notifications You must be signed in to change notification settings

c-w-a/yolov5-deeplearning-notebook

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

YOLOv5-deeplearning-notebook

example: (catbot3000)

linkedin-version(1)

experimenting with the YOLOv5 object detection algorithm and the YouTube Bounding Boxes dataset..

AUTOMATED SO FAR:

  • class selection from the YouTube Bounding Boxes dataset
  • downloading the videos (now about ~3x faster using multithreading)
  • extracting frames (now much faster by only calling ffmpeg once per video..)
  • generating labels in YOLOv5-ready format
  • remapping selected classes for YOLOv5 (zero indexed)
  • splitting the dataset and organizing files appropriately for YOLOv5 training

About

a simple notebook that allows for easy experimentation with the YOLOv5 object detection algorithm and YouTube Bounding Box dataset

Topics

Resources

License

Stars

Watchers

Forks

Languages