Checks / performance
Very high dropout rate
Check R13. 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
performance
R13
| Trigger | Any dropout layer with p > 0.65. |
|---|---|
| Why | Common dropout rates are 0.1 to 0.5. Anything above 0.65 usually indicates a typo or a confused regularization strategy. |
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.
← R12 Deep network with no normalization ยท R14 Very large activation tensor →