Skip to content

sichkar-valentyn/1-million-images-for-Traffic-Signs-Classification-tasks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 

Repository files navigation

🛑 1 million images for Traffic Signs Classification tasks

Applied geometric transformations for Traffic Signs images


🎓 Related Course

Design, Train & Test deep CNN for Image Classification. Join the course & enjoy new opportunities to get deep learning skills: https://www.udemy.com/course/convolutional-neural-networks-for-image-classification/

CNN Course


🗺️ Concept Map of the Course

Concept map


👉 Join the Course

https://www.udemy.com/course/convolutional-neural-networks-for-image-classification/


🚩 Dataset description

Three main versions at the time: "original", "light" and "hard". Geometric transformations Original version Light version Hard version


🔗 Dataset itself

Explore dataset used for training custom classifier here:

https://www.kaggle.com/valentynsichkar/traffic-signs-1-million-images-for-classification


Acknowledgements

Initial data is The German Traffic Sign Recognition Benchmarks (GTSRB).


MIT License

Copyright (c) 2020 Valentyn N Sichkar

github.com/sichkar-valentyn

Reference to:

Valentyn N Sichkar. Traffic Signs images for training custom deep CNN // GitHub platform

Releases

No releases published

Packages

No packages published