Checks / structure
Conv stride larger than kernel
Check R22. 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
R22
| Trigger | A downsampling convolution (conv1d/2d/3d, depthwise, or separable) has stride > kernelSize. |
|---|---|
| Why | The kernel jumps past its own footprint each step, so a band of the input is never read, a silent loss of information. Non-overlapping patches use stride == kernel (e.g. ViT 16/16); stride > kernel is almost always a typo. |
| Source | Convolution arithmetic: Dumoulin & Visin 2016. |
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.
← R21 Dropout immediately before Output ยท R23 Non-spatial tensor into Conv →