Get startedMeasure one executable model version on a declared benchmark or custom held-out dataset with frozen thresholds, metrics, uncertainty, and sample evidence.
Source reviewed 2026-09-23. Availability depends on your installation, permissions, and compatible runtimes. A supported path is not a guarantee of model quality or production readiness.
Start here
What you need to know first
Check the inputs below before starting. If you are new, begin with the first-project guide. A dataset holds media and labels; a model produces results; a deployment makes a selected model version callable. Creating one does not create the others.
Bring these inputs
- One exact model version
- An immutable benchmark and metric configuration
Expected output and limits
- Evaluation run with metrics and examples
- A release decision or failure-analysis queue
Core workflow
- 01
Run the first quick check
From an empty Evaluations page, set up the public object detector on the labeled COCO sample. Run the quick check to inspect real predictions and diagnostic metrics. This example is not a release benchmark or evidence of performance on your own data.
- 02
Choose the evidence path
Use a reviewed benchmark or declare a custom validation, test, stress, or out-of-distribution contract.
- 03
Validate the contract
Confirm the held-out split, distribution, provenance, labels or explicit class mapping, thresholds, seed, and acceptance criteria before queueing.
- 04
Interrogate failures
Inspect AP50-95, AP75, average recall, per-class performance, confidence reliability, size slices, failure types, thresholds, and examples. Image previews start at the saved report confidence; adjusting the preview does not change the saved evaluation or carry into another report.
- 05
Record the decision
Attach the measured run to a release gate or feed hard examples back into data work.
What this surface supports
- COCO-style AP and average recall with an explicit protocol
- Threshold and confidence-reliability analysis
- Bootstrap confidence intervals
- Wrong-class, localization, duplicate, background, and missed-object diagnostics
- Per-class and diagnostic object-size metrics
- Measured p50/p95/p99 latency and serial inference rate
- Saved reproducible configurations via Save setup for reuse
Expert section
Contracts, signals, and failure modes
Use this section when you are defining acceptance criteria, automating the surface, or reviewing whether its output is safe to promote downstream.
Expert release checklist
- Inputs and dependencies are pinned to immutable versions.
- Acceptance metrics include critical classes and operating slices.
- Failure, retry, cost, and rollback behavior are understood.
- The resulting artifact has an owner and a downstream review path.