FluxML/Flux.jl

More robust testing for AlphaDropout

クローズ

#1,851 opened on 2022/01/27

 (6 件のコメント) (0 件のリアクション) (0 人の担当者)Julia (619 件のフォーク)batch import
good first issuehelp wantedtesting

Repository metrics

Stars
 (4,725 個のスター)
PR merge metrics
 (平均マージ 3d 6h) (30d で 6 merged PRs)

説明

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.

コントリビューターガイド