In this project, you will use what you've learned about deep neural networks and convolutional neural networks to classify traffic signs. You will train a model so it can decode traffic signs from natural images by using the German Traffic Sign Dataset. After the model is trained, you will then test your model program on new images of traffic signs you find on the web, or, if you're feeling adventurous pictures of traffic signs you find locally!
This lab requires:
The lab enviroment can be created with CarND Term1 Starter Kit. Click here for the details.
- Download the dataset. This is a pickled dataset in which we've already resized the images to 32x32.
- Clone the project and start the notebook.
git clone https://github.com/udacity/CarND-Traffic-Sign-Classifier-Project
cd CarND-Traffic-Sign-Classifier-Project
jupyter notebook Traffic_Sign_Classifier.ipynb
- Follow the instructions in the
Traffic_Sign_Recognition.ipynb
notebook.
- Initial Attempt:
The work follows Le-Net architecture without much pre-processing:
2 convolution layers followed by 2 fully connected layers.
I created visualizations to better understand the nature of training. Courtesy Martin Groners tensorflowvisu file to which I made modifications.
- Run the tf_traffic_sign_classification.py file and the visualizations spring to life. Don't forget to download the traffic-sign-data.zip file and unzip it before proceeding forward.