/traffic

recognizing traffic signs using neural networks

Primary LanguagePython

RECOGNISING TRAFFIC SIGNS
Dataset: German Traffic Sign Recognition Benchmark (GTSRB)

The German Traffic Sign Benchmark is a multi-class, single-image classification challenge held at the International Joint Conference on Neural Networks (IJCNN) 2011.

  • 43 classes
  • More than 50,000 images in total

    • Accuracy achieved: 97.5%

    Usage: python traffic.py data_directory [model.h5]

  • data_directory is the directory where the photos are stored
  • model.h5 (optional) is the filename in which user wants to store the final model
    • e.g. python3 traffic.py gtsrb model.h5