Traffic-sign-classification-using-CNN

1.All the necessary libraries were imported.
2.Image visualization was done.
3.The RGB images were normalized and also converted to grayscale images(with 1 channel).
4.The CNN model was built using tensorflow and keras using "Sparse categorical cross entropy" as the Loss function.
5.The training performance was assessed using accuracy as the metric.
6.The model was then evaluated on the test set.