FluxML/Flux.jl

More robust testing for AlphaDropout

Geschlossen

#1.851 geöffnet am 27.01.2022

 (6 Kommentare) (0 Reaktionen) (0 zugewiesene Personen)Julia (619 Forks)batch import
good first issuehelp wantedtesting

Repository-Metriken

Stars
 (4.725 Sterne)
PR-Merge-Metriken
 (Durchschn. Merge 3T 6h) (6 gemergte PRs in 30 T)

Beschreibung

We currently borrow from https://github.com/pytorch/pytorch/blob/v1.10.0/test/cpp/api/modules.cpp#L1337-L1338, but some sort of goodness-of-fit test would be more robust than a simple range. Sampling the layer outputs should have a negligible impact on test runtime.

Contributor Guide