再トレーニングループを自動化する

from ultralytics import YOLO

model = YOLO("pills-v1.pt")  # デプロイ済みモデルのbest.pt
model.train(data="medical-pills.yaml", epochs=5, imgsz=320, optimizer="SGD", lr0=0.001, name="v2-finetune")

DATA = "medical-pills.yaml"  # ホールドアウトデータセットのYAMLまたはul:// URI
BASELINE, CANDIDATE = "pills-v1.pt", "pills-v2.pt"  # デプロイ済みモデルと再トレーニング候補

PASS mAP50-95 0.659 -> 0.687 beats noise
PASS every class keeps 90% of its AP (weak: none)
PASS inference 4.0 ms within 100 ms
verdict: ship the candidate

import time

from ultralytics_platform import Platform

OWNER, DEPLOYMENT = "your-username", "pill-detector-st-ghislain"
PROJECT, NEW_MODEL = "pill-inspection", "v2-finetune"

with Platform() as client:  # reads ULTRALYTICS_API_KEY
    body = {"action": "replace", "project": PROJECT, "model": NEW_MODEL}
    reply = client.deployments.update(OWNER, DEPLOYMENT, body=body)
    print(reply["status"], "-", reply["message"])  # "deploying" while the new model starts
    while (deployment := client.deployments.retrieve(OWNER, DEPLOYMENT)["deployment"])["status"] == "deploying":
        time.sleep(15)
    print(f"status={deployment['status']} model={deployment.get('model')}")
    if deployment.get("model") != NEW_MODEL:  # a failed rollout leaves the previous model serving
        raise SystemExit("Replacement failed; the previous model is still live")

deploying - Replacement model is deploying
status=ready model=v2-finetune

# Retraining runbook: pill-detector

## Trigger
- Holdout mAP50-95 more than 1 point below baseline for 2 consecutive weeks, OR
- Batch Annotation edit rate above 25% on a new batch.

## Steps
1. Collect: Save to dataset from Monitoring, plus the "Collect Uncertain Detections" agent into pill-review.
2. Label: Batch Annotation with the deployed model at the swept threshold; review every image; record the edit rate.
3. Merge into the training dataset; rerun the duplicate check, class audit, and Clustering.
4. Create dataset version v(n+1) with a description of what changed.
5. Fine-tune from the deployed model with Save Dataset Version on; optimizer SGD, lr0 0.001.
6. Run gate.py against the deployed model on the holdout. Stop here on any FAIL.
7. ML lead approves; CI runs release.py.
8. Watch endpoint_check.py for 24 hours; start a new holdout baseline.

## Rollback
- Run release.py with NEW_MODEL set to the previous version. Never delete that model while it's the rollback target.

## Owner
- ML lead approves step 7. On-call runs steps 1-6 and 8.

   Week 1   : Holdout alert. Collect, label, retrain, gate, release v(n+1).
   Week 2-3 : Quiet. Checks green.
   Week 4   : New defect class requested. Label, new version, retrain v(n+2).
   Week 5-7 : Quiet.
   Week 8   : Second plant in Poland. Check regions; add an endpoint in europe-central2.
   Week 9-11: Quiet.
   Week 12  : Quarterly holdout refresh and review.