FluxML/Flux.jl

More robust testing for AlphaDropout

Chiusa

#1851 aperta il 27 gen 2022

 (6 commenti) (0 reazioni) (0 assegnatari)Julia (619 fork)batch import
good first issuehelp wantedtesting

Metriche repository

Star
 (4725 stelle)
Metriche merge PR
 (Merge medio 3g 6h) (6 PR mergiate in 30 g)

Descrizione

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.

Guida contributor