Skip to content

karbogas/traffic4cast

Repository files navigation

traffic4cast

This is the code belonging to the Master Thesis of Konstantin Arbogast in Spring 2020 at ETH Zürich. Graph Convolutional Neural Networks are used to predict traffic data from the Traffic4cast competition 2019.

Howto

PreProcessing.py starts the data preprocessing. Settings can be changed in configPreprocess.py

main.py starts the training. Settings can be changed in configMain.py

MSEWholeImages.py calculates the MSE of the graph model on the entire image. Settings can be changed in configValidation.py

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages