TorchMetrics - Measuring Reproducibility in PyTorch

N. Detlefsen,Jiri Borovec,Justus Schock,A. Jha,Teddy Koker,Luca Di Liello,Daniel Stancl,Changsheng Quan,Maxim Grechkin,William Falcon

Published 2022 in Journal of Open Source Software

ABSTRACT

A main problem with reproducing machine learning publications is the variance of metric implementations across papers. A lack of standardization leads to different behavior in mechanisms such as checkpointing, learning rate schedulers or early stopping, that will influence the reported results. For example, a complex metric such as Fréchet inception distance (FID) for synthetic image quality evaluation (Heusel et al., 2017) will differ based on the specific interpolation method used.

PUBLICATION RECORD

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

CITED BY

Showing 1-100 of 212 citing papers · Page 1 of 3