initial version to train yolo model

examples/meter-detection/source/train.py

@@ -0,0 +1,148 @@
+#!/usr/bin/env python3
+"""SageMaker entry point for YOLO electric meter detection training."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import os
+import shutil
+from pathlib import Path
+from typing import Any
+
+import yaml
+from ultralytics import YOLO  # type: ignore[reportMissingImports]
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--model", default="yolo26n.pt")
+    parser.add_argument("--epochs", type=int, default=25)
+    parser.add_argument("--imgsz", type=int, default=640)
+    parser.add_argument("--batch", type=int, default=16)
+    parser.add_argument("--workers", type=int, default=2)
+    parser.add_argument("--patience", type=int, default=20)
+    parser.add_argument("--device", default=None)
+    parser.add_argument("--data-yaml", default=None)
+    parser.add_argument("--train-dir", default=os.environ.get("SM_CHANNEL_TRAIN", "/opt/ml/input/data/train"))
+    parser.add_argument("--model-dir", default=os.environ.get("SM_MODEL_DIR", "/opt/ml/model"))
+    return parser.parse_args()
+
+
+def find_data_yaml(train_dir: Path, explicit_path: str | None) -> Path:
+    if explicit_path:
+        data_yaml = Path(explicit_path)
+        if data_yaml.is_file():
+            return data_yaml
+        raise FileNotFoundError(f"Configured data.yaml does not exist: {data_yaml}")
+
+    matches = sorted(train_dir.rglob("data.yaml"))
+    if not matches:
+        raise FileNotFoundError(f"Could not find data.yaml under {train_dir}")
+    if len(matches) > 1:
+        print(f"Found multiple data.yaml files; using {matches[0]}")
+    return matches[0]
+
+
+def _split_exists(dataset_root: Path, value: Any) -> bool:
+    if value is None:
+        return False
+    split_path = Path(str(value))
+    if split_path.is_absolute():
+        return split_path.exists()
+    return (dataset_root / split_path).exists()
+
+
+def prepare_data_yaml(data_yaml: Path) -> Path:
+    """Write a SageMaker-local data file with absolute dataset paths."""
+    dataset_root = data_yaml.parent
+    data = yaml.safe_load(data_yaml.read_text(encoding="utf-8"))
+    if not isinstance(data, dict):
+        raise ValueError(f"Expected a mapping in {data_yaml}")
+
+    normalized = dict(data)
+    normalized["path"] = str(dataset_root)
+
+    for split_name in ("train", "val", "valid", "test"):
+        split_value = normalized.get(split_name)
+        if split_value is None:
+            continue
+        split_path = Path(str(split_value))
+        if split_path.is_absolute():
+            normalized[split_name] = str(split_path)
+        else:
+            normalized[split_name] = str((dataset_root / split_path).resolve())
+
+    if "val" not in normalized and "valid" in normalized:
+        normalized["val"] = normalized["valid"]
+
+    if not _split_exists(dataset_root, normalized.get("train")):
+        raise FileNotFoundError(f"Could not resolve train split from {data_yaml}")
+    if not _split_exists(dataset_root, normalized.get("val")):
+        raise FileNotFoundError(f"Could not resolve validation split from {data_yaml}")
+
+    prepared_path = dataset_root / "data.sagemaker.yaml"
+    prepared_path.write_text(yaml.safe_dump(normalized, sort_keys=False), encoding="utf-8")
+    print(f"Prepared dataset config: {prepared_path}")
+    return prepared_path
+
+
+def copy_if_exists(source: Path, destination: Path) -> None:
+    if source.exists():
+        shutil.copy2(source, destination)
+        print(f"Saved {destination}")
+
+
+def main() -> None:
+    args = parse_args()
+    train_dir = Path(args.train_dir)
+    model_dir = Path(args.model_dir)
+    model_dir.mkdir(parents=True, exist_ok=True)
+
+    data_yaml = prepare_data_yaml(find_data_yaml(train_dir, args.data_yaml))
+    model = YOLO(args.model)
+
+    train_kwargs: dict[str, Any] = {
+        "data": str(data_yaml),
+        "epochs": args.epochs,
+        "imgsz": args.imgsz,
+        "batch": args.batch,
+        "workers": args.workers,
+        "patience": args.patience,
+        "project": str(model_dir / "runs"),
+        "name": "train",
+        "exist_ok": True,
+    }
+    if args.device:
+        train_kwargs["device"] = args.device
+
+    results = model.train(**train_kwargs)
+    save_dir = Path(results.save_dir)
+    best_pt = save_dir / "weights" / "best.pt"
+    last_pt = save_dir / "weights" / "last.pt"
+    trained_weights = best_pt if best_pt.exists() else last_pt
+    if not trained_weights.exists():
+        raise FileNotFoundError(f"Could not find trained weights in {save_dir / 'weights'}")
+
+    copy_if_exists(trained_weights, model_dir / "best.pt")
+    trained_model = YOLO(str(trained_weights))
+    onnx_path = Path(trained_model.export(format="onnx", imgsz=args.imgsz))
+    copy_if_exists(onnx_path, model_dir / "model.onnx")
+
+    metrics = {
+        "model": args.model,
+        "epochs": args.epochs,
+        "imgsz": args.imgsz,
+        "batch": args.batch,
+        "workers": args.workers,
+        "patience": args.patience,
+        "data_yaml": str(data_yaml),
+        "weights": str(trained_weights),
+        "onnx": str(onnx_path),
+    }
+    (model_dir / "metrics.json").write_text(json.dumps(metrics, indent=2), encoding="utf-8")
+    print(f"Saved model artifacts to {model_dir}")
+
+
+if __name__ == "__main__":
+    main()