Checks / pattern
Deep network with no normalization
Check R12. 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
R12
| Trigger | ≥ 7 non-I/O layers and zero normalization layers (BN / LN / IN / GN / RMSNorm). |
|---|---|
| Why | Without normalization, deep nets converge slowly and are sensitive to initialization scale. |
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.
← R11 Sigmoid / Tanh in deep networks ยท R13 Very high dropout rate →