N Neurarch All checks Caught bugs Docs Open the app

Checks / structure

Pooling feeds Linear with no flatten

Check R26. 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 structure R26
TriggerA spatial pooling layer (maxpool, avgpool, adaptive pool) connects directly into a linear layer. Global pools are exempt: they already collapse spatial dims.
WhySibling of R18: pooling still emits a [channels, …spatial] map, but Linear expects a flat [batch, features] tensor, so the forward pass raises a shape error. Insert a Flatten or a Global Average Pool first.
SourceStandard CNN classifier head construction.

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.

← R25 Duplicate positional encoding  ·  R27 Flatten before attention →