How to Understand Limitations of Generative Networks - Generator datasets
Lists
Only you see this
Abstract
<p>These are the datasets used in "How to Understand Limitations of Generative Networks". The preprint is available on arXiv at: https://arxiv.org/abs/2305.16774</p><p>Four files are used in Sec.5 "Event generation":</p><ul><li>ev_truth.h5 is the true reconstruction-level sample used during training;</li><li>ev_masspeak.h5 is the sample generated from the neural network of Sec. 5.1;</li><li>ev_inn.h5 is the state-of-the-art sample used in Sec. 5.2;</li><li>ev_binn.h5 collects the Bayesian samples of Sec. 5.3;</li></ul><p>The remaining three files are used for the "Calorimeter simulation" section.<br>These are named according to the particle originating the shower: "calo_eplus.hdf5" for positrons, "calo_gamma.hdf5" for photons, and "calo_piplus.hdf5" for pions. Each sample contains 100k showers. </p><p> </p>
BibTeX
@inproceedings{heimel2023how,
author = {Theo Heimel and Luigi Favaro},
title = {{How to Understand Limitations of Generative Networks - Generator datasets}},
booktitle = {Zenodo},
year = {2023},
doi = {10.5281/zenodo.10277550},
}Loading related content...