Skip to content

tundejulius17/German-Traffic-Sign-Recognition-Benchmark-CNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

Overview

This is an implementation of a convolutional neural network for German Traffic Sign Recognition Benchmark.

Dataset

The German Traffic Sign Recognition Benchmark(GTSRB) is a multiclass, single-image classification data. The dataset was randomly divided into 7128 images to train the model and 1782 images to test the model.

Libraries

Keras, TensorFlow, scikit-learn, OpenCV

Metrics

A prediction accuracy of 97.87 % was achieved on the test dataset.

About

Multi-class, single-image classification challenge

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published