N Neurarch All checks Caught bugs Docs Open the app

Checks / ordering

Dropout directly before BatchNorm

Check R06. Runs in the editor as you build, in CI through the GitHub Action, and over the wire at POST /api/v1/check. Milliseconds, before any GPU is billed.

info ordering R06
TriggerA dropout layer is connected directly upstream of a BatchNorm.
WhyDropout at train time changes the activation variance; BN's running statistics get distorted. A known train-vs-eval mismatch.
SourceLi et al. 2018, "Understanding the Disharmony Between Dropout and Batch Normalization".

Why it is not a lint you can ignore

A structural mistake does not fail at review time and it does not fail at import time. It fails when the module is constructed on the training node, after the job was queued and the dataset was downloaded. That is why this runs before the spend and not after it.
Run this check on your own model Free, no account needed

Every check

41 structural checks: 6 guardrail gates and 35 architecture advisor rules. See the full catalogue.

← R05 BatchNorm / LayerNorm after activation  ยท  R07 Softmax / Sigmoid directly before Output →