More robust testing for AlphaDropout · FluxML/Flux.jl#1851

(6 留言) (0 反應) (0 負責人)Julia (4,725 star) (619 fork)batch import

good first issuehelp wantedtesting

描述

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.

技術棧: 無
領域: testingmachine learning
議題類型: test
難度: 3
預計時間: 1-3 hours
活動狀態: stale
清晰度: mostly clear
前置要求: Julia basicsFlux libraryStatistical testing
新手友善度: 70
研究方向: Examine the existing AlphaDropout test in Flux.jl's test suite, likely in test/layers.jl or similar. The issue suggests replacing the simple range check with a goodness of fit test, such as a chi squared test, to verify the dropout distribution. Review the PyTorch reference (test/cpp/api/modules.cpp lines 1337-1338) for inspiration, but adapt to Julia's testing framework. Consider implementing a statistical test that checks whether the output distribution matches the expected AlphaDropout distribution.