Upload face_utils.py

face_utils.py

@@ -0,0 +1,43 @@
+import numpy as np
+from PIL import Image, ImageDraw
+from facenet_pytorch import MTCNN
+
+class FaceCropper:
+    """Detect faces and return (cropped_face, annotated_image)."""
+    def __init__(self, device: str | None = None, image_size: int = 224):
+        import torch
+        self.device = device or ("cuda" if torch.cuda.is_available() else "cpu")
+        self.mtcnn = MTCNN(keep_all=True, device=self.device)
+        self.image_size = image_size
+
+    def _to_pil(self, img):
+        if isinstance(img, Image.Image):
+            return img.convert("RGB")
+        return Image.fromarray(img).convert("RGB")
+
+    def detect_and_crop(self, img, select="largest"):
+        pil = self._to_pil(img)
+        boxes, probs = self.mtcnn.detect(pil)
+
+        annotated = pil.copy()
+        draw = ImageDraw.Draw(annotated)
+
+        if boxes is None or len(boxes) == 0:
+            return None, annotated, {"boxes": np.empty((0,4)), "scores": np.empty((0,))}
+
+        for b, p in zip(boxes, probs):
+            x1, y1, x2, y2 = map(float, b)
+            draw.rectangle([x1, y1, x2, y2], outline=(255, 0, 0), width=3)
+            draw.text((x1, y1-10), f"{p:.2f}", fill=(255, 0, 0))
+
+        idx = 0
+        if select == "largest":
+            areas = [(b[2]-b[0])*(b[3]-b[1]) for b in boxes]
+            idx = int(np.argmax(areas))
+        elif isinstance(select, int) and 0 <= select < len(boxes):
+            idx = select
+
+        x1, y1, x2, y2 = boxes[idx].astype(int)
+        face = pil.crop((x1, y1, x2, y2))
+
+        return face, annotated, {"boxes": boxes, "scores": probs}