German Traffic Sign Classifier — Machine Learning

  1. Exploratory Data Analysis
  2. Data Preprocessing
  3. Using VGGNet Model Architecture to be implemented with TensorFlow
  4. Model Testing using the Test Set
  5. Conclusion

1. Exploratory Data Analysis

Sample images that were plotted via matplotlib are shown below:

2. Data Preprocessing

Shuffling is used to increase randomness and variety in training dataset

3. Using VGGNet Model Architecture to be implemented with TensorFlow

4. Model Testing using the Test Set

5. Conclusion

Using VGGNet, we’ve been able to reach a test accuracy of 96.3%. Some clusters are observed in the confusion matrix. This is due to various speed limits being sometimes misclassified among themselves. Similarly, traffic signs with triangular shapes are misclassified among themselves.

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Sean Tay

Sean Tay

Pursuing a career as a Management Consultant — with a touch of Machine Learning on the side