Checks / structure
Flatten before attention
Check R27. 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
R27
| Trigger | A flatten layer connects directly into an attention layer. |
|---|---|
| Why | Flatten collapses the sequence dimension into one long vector, leaving a length-1 sequence, so attention has nothing to relate. Keep the [sequence, dim] layout and flatten only after the attention stack. |
| Source | Attention operates over a sequence axis: Vaswani et al. 2017. |
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.
← R26 Pooling feeds Linear with no flatten ยท R28 ConvTranspose checkerboard risk →