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
| Trigger | A dropout layer is connected directly upstream of a BatchNorm. |
|---|---|
| Why | Dropout at train time changes the activation variance; BN's running statistics get distorted. A known train-vs-eval mismatch. |
| Source | Li 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 →