agude / pelops

The Pelops car re-ID project

Pelops

Pelops is a project by Lab41 that uses deep learning based methods to automatically identify cars by using their large scale features—color, shape, light configuration, etc.

Install Instructions

Pelops provides several Docker containers the assist in running the project. You can build them by checking out the code and running make:

git clone https://github.com/Lab41/pelops.git
cd pelops
make

Then:

make notebook

Which will run a container containing Pelops and a notebook server.

Otherwise you can install Pelops using pip:

git clone https://github.com/Lab41/pelops.git
pip install pelops

There are several dependencies that will need to be installed. The requirements.txt should include most of them, but other programs such as keras and Tensorflow are also required. For this reason it is suggested to use the notebook container to run Pelops.

Documentation

• Turning Chips into features

Tests

Tests are currently written in pytest. The tests are automatically run when submitting pull requests.

You can run the tests in a container by calling:

make test

This will build a docker container, mount your local version of the code, and run the tests.

Contributing to Pelops

Want to contribute? Awesome!

Please make sure you have pre-commit installed so that your code is checked for various issues.

After that, send us a pull request! We're happy to review them!