Add multi-GPU Ego4D local feature extraction without symlinks

easycom_head.py

@@ -638,6 +638,30 @@ def normalize_sample_name(
         raise ValueError(f"Invalid Ego4D clip UUID: {value}") from error
 
 
+def resolve_feature_path(
+    feature_root: str | Path,
+    sample: str | int,
+    *,
+    dataset: DatasetName = "easycom",
+) -> Path:
+    """Read flat features or Ego4D train/test subdirectories without link farms.
+
+    Manifest membership, not directory discovery, determines the data split.
+    Multiple copies are rejected rather than silently choosing stale features.
+    """
+    name = normalize_sample_name(sample, dataset)
+    root = Path(feature_root)
+    candidates = [root / f"{name}.pt"]
+    if dataset == "ego4d":
+        candidates += [root / split / f"{name}.pt" for split in ("train", "test")]
+    found = [path for path in candidates if path.is_file()]
+    if len(found) > 1:
+        raise ValueError(f"Ambiguous feature copies for {name}: {found}; select one feature root")
+    if not found:
+        raise FileNotFoundError(f"No features for {name}; checked: " + ", ".join(map(str, candidates)))
+    return found[0]
+
+
 def load_ego4d_manifest_split(
     manifest: str | Path,
     split: Literal["train", "test", "all"],
@@ -727,7 +751,7 @@ def load_session_data(
     """Load and validate one saved Omni feature payload and target array."""
 
     name = normalize_sample_name(session, dataset)
-    feature_path = Path(feature_root) / f"{name}.pt"
+    feature_path = resolve_feature_path(feature_root, name, dataset=dataset)
     target_path = Path(target_root) / f"{name}.npy"
     if not feature_path.is_file():
         raise FileNotFoundError(feature_path)
@@ -804,7 +828,7 @@ def load_session_data(
         from local_turn_features import load_local_features
 
         local, contract = load_local_features(
-            Path(local_feature_root) / f"{name}.pt",
+            resolve_feature_path(local_feature_root, name, dataset=dataset),
             payload,
             sample_id=name,
             dataset=dataset,