claude_refactor_v3: New train_gtauav.py, added entry point main.py, added utils

src/utils/__init__.py

@@ -0,0 +1,2 @@
+"""Utilities: paths, seeding, IO."""
+

src/utils/io_utils.py

@@ -0,0 +1,51 @@
+"""IO helpers: atomic checkpoint saves, VRAM cleanup."""
+
+from __future__ import annotations
+
+import gc
+import logging
+import os
+import tempfile
+from pathlib import Path
+from typing import Any
+
+import torch
+
+logger = logging.getLogger(__name__)
+
+
+def atomic_save_torch(obj: Any, path: Path) -> None:
+    """Save a PyTorch object atomically via temp file + os.replace.
+
+    On any failure (KeyboardInterrupt / SIGTERM included), the temp file
+    is removed. Makes --resume safe: a partial checkpoint never lands at
+    the destination path.
+
+    Args:
+        obj: Anything torch.save can handle.
+        path: Destination path. Parent directory is created if missing.
+    """
+    path.parent.mkdir(parents=True, exist_ok=True)
+    fd, tmp = tempfile.mkstemp(suffix=".pt.tmp", dir=path.parent)
+    os.close(fd)
+    try:
+        torch.save(obj, tmp)
+        os.replace(tmp, path)
+    except BaseException:
+        if os.path.exists(tmp):
+            os.remove(tmp)
+        raise
+
+
+def clear_vram() -> None:
+    """Free VRAM and reset peak memory stats."""
+    gc.collect()
+    if torch.cuda.is_available():
+        torch.cuda.empty_cache()
+        torch.cuda.reset_peak_memory_stats()
+        allocated_gb = torch.cuda.memory_allocated() / 1e9
+        logger.info("VRAM cleared. Current usage: %.2f GB", allocated_gb)
+
+
+
+        

src/utils/path_utils.py

@@ -0,0 +1,32 @@
+"""Project root resolution via marker files."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+# Markers identifying the project root (per REQUIREMENTS_GIN_STYLE.md §5).
+_MARKERS: tuple[str, ...] = ("pyproject.toml", ".git", "in")
+
+
+def get_proj_dir() -> str:
+    """Return absolute project root with trailing slash.
+
+    Walks up from this file's directory until finding pyproject.toml,
+    .git, or in/. Searches up to 10 levels.
+
+    Returns:
+        Project root path with trailing slash, e.g. '/home/user/caption-test/'.
+
+    Raises:
+        RuntimeError: If no marker found within 10 parent directories.
+    """
+    current = Path(__file__).resolve().parent
+    for _ in range(10):
+        if any((current / m).exists() for m in _MARKERS):
+            return str(current) + "/"
+        current = current.parent
+    raise RuntimeError(
+        f"Project root not found. Looked for {_MARKERS} starting at "
+        f"{Path(__file__).resolve().parent}",
+    )
+

src/utils/seed_utils.py

@@ -0,0 +1,23 @@
+"""RNG seeding for reproducibility."""
+
+from __future__ import annotations
+
+import random
+
+import numpy as np
+import torch
+
+
+def set_seed(seed: int = 42) -> None:
+    """Fix all RNG seeds (Python random, NumPy, PyTorch CPU + all CUDA devices).
+
+    Args:
+        seed: Integer seed.
+    """
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    torch.cuda.manual_seed_all(seed)
+
+
+