Traffic Sign Recognition

Overview

In this project, I will show you how to use PyTorch to classify traffic signs and how to imporve the classifier with a Spatial Transformer Networks. 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 on new iamges of traffic signs from test dataset.

The model is designed using Spatial Transformer Network with a modified version of IDSIA networks and trained with heavily augmented data. The models reaches about 99.3% test set accuracy

My attempt to tackle this problem can be read in report.

Configure and Manage Your Environment with Anaconda

Per the Anaconda docs:

Conda is an open source package management system and environment management system for installing multiple versions of software packages and their dependencies and switching easily between them. It works on Linux, OS X and Windows, and was created for Python programs but can package and distribute any software.

Using Anaconda consists of the following:

1. Install miniconda on your computer, by selecting the latest Python version for your operating system. If you already have conda or miniconda installed, you should be able to skip this step and move on to step 2.
2. Create and activate * a new conda environment.

* Each time you wish to work on any exercises, activate your conda environment!

1. Installation

Download the latest version of miniconda that matches your system.

Install miniconda on your machine. Detailed instructions:

• Linux: http://conda.pydata.org/docs/install/quick.html#linux-miniconda-install
• Mac: http://conda.pydata.org/docs/install/quick.html#os-x-miniconda-install
• Windows: http://conda.pydata.org/docs/install/quick.html#windows-miniconda-install

2. Create and Activate the Environment

For Windows users, these following commands need to be executed from the Anaconda prompt as opposed to a Windows terminal window. For Mac, a normal terminal window will work.

1. Clone the repository, and navigate to the downloaded folder. This may take a minute or two to clone due to the included image data.

git clone https://github.com/wolfapple/traffic-sign-recognition.git
cd traffic-sign-recognition

2. Create (and activate) a new environment, named traffic-sign-recognition. Running this command will create a new conda environment that is provisioned with all libraries you need to be successful in this program.

• Linux or Mac:

conda env create -f environment.yaml
source activate traffic-sign-recognition

• Windows:

conda env create -f environment.yaml
activate traffic-sign-recognition

At this point your command line should look something like: (traffic-sign-recognition) <User>:traffic-sign-recognition <user>$. The (traffic-sign-recognition) indicates that your environment has been activated, and you can proceed with further package installations.

3. Verify that the environment was created in your environments:

conda info --envs

4. Cleanup downloaded libraries (remove tarballs, zip files, etc):

conda clean -tp

5. That's it!

Now most of the libraries are available to you. Very occasionally, you will see a repository with an addition requirements file, which exists should you want to use TensorFlow and Keras, for example. In this case, you're encouraged to install another library to your existing environment, or create a new environment for a specific project.

To exit the environment when you have completed your work session, simply close the terminal window.

3. Uninstalling

To uninstall the environment:

conda env remove -n traffic-sign-recognition

Dataset

The GTSRB dataset (German Traffic Sign Recognition Benchmark) is provided by the Institut für Neuroinformatik group here. It was published for a competition held in 2011 (results). Images are spread across 43 different types of traffic signs and contain a total of 39,209 train examples and 12,630 test ones.

1. Download the dataset. This is a pickled dataset in which resized the images to 32x32.

2. Unzip the dataset into ./data directory.

Training and validating model

Run the script train.py to train the model.

python train.py

You can include one or more command line arguments.

python train.py --help

Various training options can be confirmed with the following command.

Evaluating the model on the test set

As the model trains, model checkpoints are saved to model.pt file to the current working directory. You can take one of the checkpoints and run:

python evaluate.py --data [data_dir] --model [model_file]

We want to visualize the output of the spatial transformers layer after the training, we visualize a batch of input images and the corresponding transformed batch using STN. Check the generated image file.