feat: remove object mode pipeline (YOLO, SigLIP, TRAINING_MODE, OBJECT_CLASS)

winnow is a face recognition training tool. Object mode required manual
file placement with no Frigate API, pulled in torch/torchvision/transformers/
ultralytics (~2 GB), and was architecturally misaligned with the project goal.

Removed:
- process_object_mode (YOLO inference), get_yolo_model
- SigLIP model stack (get_siglip_model, get_object_embedding, batch variant)
- entity_type branching throughout diversity, embeddings, jobs, executor
- TRAINING_MODE and OBJECT_CLASS env vars
- torch, torchvision, transformers, ultralytics dependencies
- pytorch index entries from pyproject.toml
- Object mode from README (Modes section, env var table, How It Works)

winnow/image_processing.py

@@ -1,4 +1,4 @@
-"""Image processing functions for cropping faces and objects."""
+"""Image processing functions for cropping faces."""
 
 import logging
 import os
@@ -10,9 +10,6 @@ from .config import Config
 
 logger = logging.getLogger(__name__)
 
-# Lazy singleton
-_yolo_model = None
-
 
 def _save_jpeg(img: Image.Image, path: str) -> None:
     if img.mode != "RGB":
@@ -20,17 +17,6 @@ def _save_jpeg(img: Image.Image, path: str) -> None:
     img.save(path, format="JPEG")
 
 
-def get_yolo_model():
-    """Singleton for YOLO model."""
-    global _yolo_model
-    if _yolo_model is None:
-        from ultralytics import YOLO
-
-        logger.info("Loading YOLOv9c model...")
-        _yolo_model = YOLO("yolov9c.pt")
-    return _yolo_model
-
-
 def align_face(img: Image.Image, landmarks: list[list[float]] | np.ndarray) -> Image.Image | None:
     """Align face using 5-point landmarks to standard ArcFace input format (112x112).
 
@@ -170,49 +156,4 @@ def process_face_mode(
     return face_crop.size
 
 
-def process_object_mode(
-    img: Image.Image,
-    config: dict,
-    output_dir: str,
-    count: int,
-) -> bool:
-    """Detect and crop objects using YOLO."""
-    try:
-        model = get_yolo_model()
-        target_class = config.get("object_class", "dog")
-        import torch
-
-        if os.getenv("FORCE_CPU", "").lower() in ("true", "1", "yes"):
-            device = "cpu"
-        elif hasattr(torch, "xpu") and torch.xpu.is_available():
-            device = "xpu"
-        else:
-            device = None  # YOLO auto-selects (CUDA/ROCm/CPU)
-
-        results = model(img, verbose=False, device=device)
-
-        found = False
-        class_idx = 0  # Sequential counter per target class (Issue #10)
-        for box in (box for r in results for box in r.boxes):
-            cls_id = int(box.cls[0])
-            conf = float(box.conf[0])
-            if 0 <= cls_id < len(model.names) and model.names[cls_id] == target_class and conf > 0.5:
-                x1, y1, x2, y2 = box.xyxy[0].tolist()
-                _save_jpeg(
-                    img.crop((x1, y1, x2, y2)),
-                    os.path.join(output_dir, f"{count}_{class_idx}.jpg"),
-                )
-                class_idx += 1
-                found = True
-
-        return found
-    except Exception as e:
-        logger.error(f"YOLO processing failed: {e}")
-        return False
-
-
-def process_full_mode(img: Image.Image, output_dir: str, count: int) -> bool:
-    """Save full image."""
-    _save_jpeg(img, os.path.join(output_dir, f"{count}.jpg"))
-    return True