Checks / ordering
Dropout immediately before Output
Check R21. 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.
warn
ordering
R21
| Trigger | A dropout layer is the last node before the output node. |
|---|---|
| Why | In training this randomly zeroes the final logits fed to the loss; at eval it is a no-op, so train and eval behaviour diverge. Dropout belongs before the final projection (Linear/Conv), not after it. |
| Source | Srivastava et al. 2014 (Dropout): dropout regularizes hidden representations, not output logits. |
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.
← R20 Linear → Linear with no activation · R22 Conv stride larger than kernel →