Update app.py

app.py

@@ -167,37 +167,98 @@ async def predict_single_dog(image):
     return top1_prob, topk_breeds, topk_probs_percent
     
 
-async def detect_multiple_dogs(image, conf_threshold=0.25, iou_threshold=0.4):
+# async def detect_multiple_dogs(image, conf_threshold=0.25, iou_threshold=0.4):
+#     results = model_yolo(image, conf=conf_threshold, iou=iou_threshold)[0]
+#     dogs = []
+#     boxes = []
+#     for box in results.boxes:
+#         if box.cls == 16:  # COCO dataset class for dog is 16
+#             xyxy = box.xyxy[0].tolist()
+#             confidence = box.conf.item()
+#             boxes.append((xyxy, confidence))
+    
+#     if not boxes:
+#         dogs.append((image, 1.0, [0, 0, image.width, image.height]))
+#     else:
+#         nms_boxes = non_max_suppression(boxes, iou_threshold)
+        
+#         for box, confidence in nms_boxes:
+#             x1, y1, x2, y2 = box
+#             w, h = x2 - x1, y2 - y1
+#             x1 = max(0, x1 - w * 0.05)
+#             y1 = max(0, y1 - h * 0.05)
+#             x2 = min(image.width, x2 + w * 0.05)
+#             y2 = min(image.height, y2 + h * 0.05)
+#             cropped_image = image.crop((x1, y1, x2, y2))
+#             dogs.append((cropped_image, confidence, [x1, y1, x2, y2]))
+    
+#     return dogs
+
+
+# def non_max_suppression(boxes, iou_threshold):
+#     keep = []
+#     boxes = sorted(boxes, key=lambda x: x[1], reverse=True)
+#     while boxes:
+#         current = boxes.pop(0)
+#         keep.append(current)
+#         boxes = [box for box in boxes if calculate_iou(current[0], box[0]) < iou_threshold]
+#     return keep
+
+# def calculate_iou(box1, box2):
+#     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])
+    
+#     iou = intersection / float(area1 + area2 - intersection)
+#     return iou
+
+
+async def detect_multiple_dogs(image, conf_threshold=0.15, iou_threshold=0.3):
     results = model_yolo(image, conf=conf_threshold, iou=iou_threshold)[0]
     dogs = []
     boxes = []
+    
     for box in results.boxes:
         if box.cls == 16:  # COCO dataset class for dog is 16
             xyxy = box.xyxy[0].tolist()
             confidence = box.conf.item()
             boxes.append((xyxy, confidence))
-    
+
+    # 如果沒有檢測到任何狗
     if not boxes:
         dogs.append((image, 1.0, [0, 0, image.width, image.height]))
     else:
         nms_boxes = non_max_suppression(boxes, iou_threshold)
         
+        # 進一步優化處理重疊框邏輯
         for box, confidence in nms_boxes:
             x1, y1, x2, y2 = box
             w, h = x2 - x1, y2 - y1
-            x1 = max(0, x1 - w * 0.05)
-            y1 = max(0, y1 - h * 0.05)
-            x2 = min(image.width, x2 + w * 0.05)
-            y2 = min(image.height, y2 + h * 0.05)
+            
+            # 計算高度和寬度的比率，如果比例異常，則認定為重疊框需要拆分
+            aspect_ratio = h / w if w != 0 else 1
+            if aspect_ratio > 1.5 or aspect_ratio < 0.5:
+                # 假設重疊度過高，可以進一步裁切框
+                x1 = max(0, x1 - w * 0.05)
+                y1 = max(0, y1 - h * 0.05)
+                x2 = min(image.width, x2 + w * 0.05)
+                y2 = min(image.height, y2 + h * 0.05)
+            
             cropped_image = image.crop((x1, y1, x2, y2))
             dogs.append((cropped_image, confidence, [x1, y1, x2, y2]))
-    
-    return dogs
 
+    return dogs
 
-def non_max_suppression(boxes, iou_threshold):
+# 增加一個優化的non_max_suppression版本
+def non_max_suppression(boxes, iou_threshold=0.3):
     keep = []
-    boxes = sorted(boxes, key=lambda x: x[1], reverse=True)
+    boxes = sorted(boxes, key=lambda x: x[1], reverse=True)  # 按信心分數排序
+    
     while boxes:
         current = boxes.pop(0)
         keep.append(current)
@@ -210,14 +271,17 @@ def calculate_iou(box1, box2):
     x2 = min(box1[2], box2[2])
     y2 = min(box1[3], box2[3])
     
+    # 計算交集面積
     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])
     
+    # 計算IOU
     iou = intersection / float(area1 + area2 - intersection)
     return iou
 
 
+
 async def process_single_dog(image):
     top1_prob, topk_breeds, topk_probs_percent = await predict_single_dog(image)
     if top1_prob < 0.2: