The Umami documentation is avaliable here:
Below is included a brief summary on how to get started fast.
You can find the detailed described in the umami docs.
To better collaborate on this project, we require some code practices such as:
- linting (
flake8,yamllint) - unit tests
- integration tests
More details can be found here.
For the training of umami the ntuples are used as specified in the section MC Samples.
The ntuples need to be preprocessed following the Preprocessing Instructions.
If you want to train or evaluate DL1r or DIPS please follow the Training Instructions.
At the FTAG Workshop in 2022 in Amsterdam, we gave a tutorial how to work with Umami. You can find the slides together with a recording of the talk here. The corresponding step-by-step tutorial can be found in the FTAG docs webpage here.