iou

app.py

@@ -6,7 +6,7 @@ from sahi import AutoDetectionModel
 from PIL import Image
 import plotly.graph_objects as go
 import torch
-import spaces
+#import spaces
 
 import os
 import shutil
@@ -64,12 +64,11 @@ class Detection:
         yolov8_model_path1 = "./model/train_model.pt"  # Update to your model path
         yolov8_model_path2 = "./model/best_100epochs_latest.pt"  # Update to the second model path
 
-        # Initialize the AutoDetectionModels
         self.model1 = AutoDetectionModel.from_pretrained(
             model_type='yolov8',
             model_path=yolov8_model_path1,
             confidence_threshold=0.3,
-            device='cuda:0'  # Change to 'cpu' if not using GPU
+            device='cuda:0' 
         )
 
         self.model2 = AutoDetectionModel.from_pretrained(
@@ -80,7 +79,8 @@ class Detection:
         )
 
     def detect_from_image(self, image,slice_width_input,slice_height_input,overlap_width_input,overlap_height_input):
-        # Perform sliced prediction with both models
+
+        
         results1 = get_sliced_prediction(
             image=image,
             detection_model=self.model1,
@@ -116,10 +116,10 @@ class Detection:
 
         return combined_annotations
 
-    def combine_results(self, annotations1, annotations2, iou_threshold=0.5):
+    def combine_results(self, annotations1, annotations2, iou_threshold=0.1):
         """
-        Combine the results of two sets of annotations, keeping only the higher-confidence
-        prediction when IoU between two bounding boxes is above the threshold.
+        Combine the results of two sets of annotations, keeping the higher-confidence
+        prediction only when the IoU between two bounding boxes is above the threshold.
 
         :param annotations1: COCO annotations from model 1
         :param annotations2: COCO annotations from model 2
@@ -143,9 +143,17 @@ class Detection:
 
                 iou = box_iou(torch.tensor(box1_array), torch.tensor(box2_array)).item()
 
-                # If IoU is high and model 2 confidence is lower, discard the annotation from model 2
-                if iou > iou_threshold and conf2 <= conf1:
-                    keep = False
+                # Print IoU for debugging
+                print(f"IoU {iou:.4f}")
+
+                # Only check confidence if IoU is above the threshold
+                if iou > iou_threshold:
+                    # Keep the annotation with higher confidence
+                    if conf2 <= conf1:
+                        keep = False
+                    else:
+                        # Remove the lower-confidence annotation from `combined`
+                        combined.remove(ann1)
                     break
 
             if keep:
@@ -153,6 +161,8 @@ class Detection:
 
         return combined
 
+
+
     #-----------------------------------------------------------------------------------------------------------------------
     
     def draw_annotations(self, image, annotations):
@@ -320,7 +330,7 @@ def upload_image(image):
     """Process the uploaded image (if needed) and display it.""" 
     return image
 
-@spaces.GPU
+#@spaces.GPU
 def apply_detection(image,slice_width_input,slice_height_input,overlap_width_input,overlap_height_input):
     """Run object detection on the uploaded image and return the annotated image.""" 
     # Convert image from PIL to NumPy array