This is an implementation of a convolutional neural network for German Traffic Sign Recognition Benchmark.
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.
Keras, TensorFlow, scikit-learn, OpenCV
A prediction accuracy of 97.87 % was achieved on the test dataset.