Checks / pattern
Back-to-back normalization
Check R24. 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
pattern
R24
| Trigger | A normalization layer connects directly into another normalization layer (e.g. LayerNorm → BatchNorm). |
|---|---|
| Why | Normalizing an already-normalized tensor is redundant; the second layer mostly re-centres/re-scales what the first produced and just burns its own learnable parameters. |
| Source | Idempotence of standardization: Ioffe & Szegedy 2015. |
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.
← R23 Non-spatial tensor into Conv · R25 Duplicate positional encoding →