delete me

inference.py

@@ -31,7 +31,7 @@ class FruitVegetableDetector:
             print(f"Failed to load ONNX model: {e}. Falling back to SIMULATED mode.")
             self.session = None
 
-    def detect(self, image_rgb, confidence_threshold=0.10):
+    def detect(self, image_rgb, confidence_threshold=0.85):
         """
         Runs inference on an RGB image.
         Args:
@@ -90,8 +90,54 @@ class FruitVegetableDetector:
             
         # Sort predictions by confidence descending
         predictions = sorted(predictions, key=lambda x: x["confidence"], reverse=True)
+        
+        # Apply Non-Maximum Suppression (NMS) to eliminate duplicate/overlapping boxes
+        predictions = self.apply_nms(predictions, iou_threshold=0.5)
+        
         return predictions
 
+    def apply_nms(self, predictions, iou_threshold=0.5):
+        """
+        Applies Non-Maximum Suppression (NMS) to predictions.
+        """
+        if not predictions:
+            return []
+            
+        keep = []
+        # Predictions are already sorted by confidence descending
+        candidates = list(predictions)
+        
+        while candidates:
+            best = candidates.pop(0)
+            keep.append(best)
+            
+            remaining = []
+            for pred in candidates:
+                if self.calculate_iou(best["box"], pred["box"]) < iou_threshold:
+                    remaining.append(pred)
+            candidates = remaining
+            
+        return keep
+
+    def calculate_iou(self, box1, box2):
+        """
+        Calculates Intersection over Union (IoU) of two boxes [xmin, ymin, xmax, ymax].
+        """
+        x1 = max(box1[0], box2[0])
+        y1 = max(box1[1], box2[1])
+        x2 = min(box1[2], box2[2])
+        y2 = min(box1[3], box2[3])
+        
+        intersection = max(0, x2 - x1) * max(0, y2 - y1)
+        
+        area1 = (box1[2] - box1[0]) * (box1[3] - box1[1])
+        area2 = (box2[2] - box2[0]) * (box2[3] - box2[1])
+        union = area1 + area2 - intersection
+        
+        if union == 0:
+            return 0
+        return intersection / union
+
     def _simulate_detection(self, width, height, confidence_threshold):
         """
         Generates simulated detections based on random chances.