← Back to the chapter · Previous detail
Technical detail · Edge AI: Deployment Validation and Runtime Design
Keep evidence at each release stage
This record distinguishes successful model transfer from proof that the deployed application works. Keep the exact artifact and its target-device evidence together so reviewers can compare releases and rollback results.
| Stage | What happens | Evidence to keep |
|---|---|---|
| Train in cloud | Train and validate the full-precision model on representative data. | Dataset version, metrics, and exact model artifact. |
| Convert and optimize | Export to TensorFlow Lite/LiteRT or ONNX and quantize for the target. | On-target accuracy after conversion, not only server accuracy. |
| Deploy over the air | Roll a versioned model to a canary group first. | Device-to-model inventory, rollout ring, and rollback result. |
| Monitor | Track confidence, input statistics, alerts, sampled hard cases, and device health. | Drift signals and field cases for retraining. |