Published in


Traffic Sign Recognition using Convolutional Neural Network

Goals of the project

Project pipeline

  1. Loading the data
  2. Dataset exploration and visualization
  3. Data preprocessing
  4. Data augmentation
  5. Designing, training and testing a CNN model
  6. Using the model on new images
  7. Analyzing softmax probabilities


Data preprocessing

Designing a Deep Neural Network model

Convolutional Neural Network

from https://adeshpande3.github.io/adeshpande3.github.io/A-Beginner%27s-Guide-To-Understanding-Convolutional-Neural-Networks/
from from: https://devblogs.nvidia.com/parallelforall/deep-learning-nutshell-core-concepts/

Tuning the model

  • Initial LeNet model, choosing input images color representation — 91 %
  • Input images normalization — ~91 %
  • Training set augmantation — 93 %
  • Learn rate optimization, from this stage I tested for 100 epochs — 95 %
  • Finding optimum image transformations during training set augmentation — 96 %
  • Trying different pool methods, trying dropout, choosing L2 loss, tuning learn rate again — 96.8
  • Training set accuracy of 99.5 %
  • Validation set accuracy of 96.8 %
  • Test set accuracy of 94.6 %

Testing the model on new images




Elijah McClain, George Floyd, Eric Garner, Breonna Taylor, Ahmaud Arbery, Michael Brown, Oscar Grant, Atatiana Jefferson, Tamir Rice, Bettie Jones, Botham Jean

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