Update app.py

app.py

@@ -194,7 +194,7 @@ 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=0.3):
+async def detect_multiple_dogs(image, conf_threshold=0.2, iou_threshold=0.3):
     results = model_yolo(image, conf=conf_threshold, iou=iou_threshold)[0]
     dogs = []
     boxes = []
@@ -203,28 +203,27 @@ async def detect_multiple_dogs(image, conf_threshold=0.25, iou_threshold=0.3):
             xyxy = box.xyxy[0].tolist()
             confidence = box.conf.item()
             boxes.append((xyxy, confidence))
-
-    # 如果沒有檢測到狗，使用整張圖片
+    
     if not boxes:
         dogs.append((image, 1.0, [0, 0, image.width, image.height]))
     else:
-        # 按置信度排序
         sorted_boxes = sorted(boxes, key=lambda x: x[1], reverse=True)
-        
-        # 使用非極大值抑制（NMS）來合併重疊的框
         nms_boxes = non_max_suppression(sorted_boxes, iou_threshold)
         
         for box, confidence in nms_boxes:
             x1, y1, x2, y2 = box
-            # 擴大框的大小以包含更多上下文
             w, h = x2 - x1, y2 - y1
-            x1 = max(0, x1 - w * 0.15)
-            y1 = max(0, y1 - h * 0.15)
-            x2 = min(image.width, x2 + w * 0.15)
-            y2 = min(image.height, y2 + h * 0.15)
+            x1 = max(0, x1 - w * 0.1)
+            y1 = max(0, y1 - h * 0.1)
+            x2 = min(image.width, x2 + w * 0.1)
+            y2 = min(image.height, y2 + h * 0.1)
             cropped_image = image.crop((x1, y1, x2, y2))
             dogs.append((cropped_image, confidence, [x1, y1, x2, y2]))
-
+        
+        # 如果只檢測到一隻狗，但置信度較低，添加整張圖片作為備選
+        if len(dogs) == 1 and dogs[0][1] < 0.5:
+            dogs.append((image, 1.0, [0, 0, image.width, image.height]))
+    
     return dogs
 
 def non_max_suppression(boxes, iou_threshold):
@@ -447,69 +446,6 @@ async def process_single_dog(image):
 #     iface.launch()
 
 
-# async def predict(image):
-#     if image is None:
-#         return "Please upload an image to start.", None, gr.update(visible=False, choices=[]), None
-
-#     try:
-#         if isinstance(image, np.ndarray):
-#             image = Image.fromarray(image)
-
-#         dogs = await detect_multiple_dogs(image)
-        
-#         color_list = ['#FF0000', '#00FF00', '#0000FF', '#FFFF00', '#00FFFF', '#FF00FF', '#800080', '#FFA500']
-#         explanations = []
-#         buttons = []
-#         annotated_image = image.copy()
-#         draw = ImageDraw.Draw(annotated_image)
-#         font = ImageFont.load_default()
-
-#         for i, (cropped_image, _, box) in enumerate(dogs):
-#             top1_prob, topk_breeds, topk_probs_percent = await predict_single_dog(cropped_image)
-#             color = color_list[i % len(color_list)]
-#             draw.rectangle(box, outline=color, width=3)
-#             draw.text((box[0], box[1]), f"Dog {i+1}", fill=color, font=font)
-
-#             if top1_prob >= 0.5:
-#                 breed = topk_breeds[0]
-#                 description = get_dog_description(breed)
-#                 formatted_description = format_description(description, breed)
-#                 explanations.append(f"Dog {i+1}: {formatted_description}")
-#             elif top1_prob >= 0.2:
-#                 dog_explanation = f"Dog {i+1}: Top 3 possible breeds:\n"
-#                 dog_explanation += "\n".join([f"{j+1}. **{breed}** ({prob} confidence)" for j, (breed, prob) in enumerate(zip(topk_breeds[:3], topk_probs_percent[:3]))])
-#                 explanations.append(dog_explanation)
-#                 buttons.extend([f"Dog {i+1}: More about {breed}" for breed in topk_breeds[:3]])
-#             else:
-#                 explanations.append(f"Dog {i+1}: The image is unclear or the breed is not in the dataset.")
-
-#         final_explanation = "\n\n".join(explanations)
-#         if buttons:
-#             final_explanation += "\n\nClick on a button to view more information about the breed."
-#             initial_state = {
-#                 "explanation": final_explanation,
-#                 "buttons": buttons,
-#                 "show_back": True,
-#                 "image": annotated_image,
-#                 "is_multi_dog": len(dogs) > 1,
-#                 "dogs_info": explanations
-#             }
-#             return final_explanation, annotated_image, gr.update(visible=True, choices=buttons), initial_state
-#         else:
-#             initial_state = {
-#                 "explanation": final_explanation,
-#                 "buttons": [],
-#                 "show_back": False,
-#                 "image": annotated_image,
-#                 "is_multi_dog": len(dogs) > 1,
-#                 "dogs_info": explanations
-#             }
-#             return final_explanation, annotated_image, gr.update(visible=False, choices=[]), initial_state
-
-#     except Exception as e:
-#         error_msg = f"An error occurred: {str(e)}\n\nTraceback:\n{traceback.format_exc()}"
-#         print(error_msg)
-#         return error_msg, None, gr.update(visible=False, choices=[]), None
 
 async def predict(image):
     if image is None:
@@ -528,27 +464,27 @@ async def predict(image):
         draw = ImageDraw.Draw(annotated_image)
         font = ImageFont.load_default()
 
-        for i, (cropped_image, _, box) in enumerate(dogs):
+        for i, (cropped_image, detection_confidence, box) in enumerate(dogs):
             top1_prob, topk_breeds, topk_probs_percent = await predict_single_dog(cropped_image)
             color = color_list[i % len(color_list)]
             draw.rectangle(box, outline=color, width=3)
             draw.text((box[0], box[1]), f"Dog {i+1}", fill=color, font=font)
 
-            if top1_prob >= 0.5:
+            # 結合 YOLO 檢測置信度和品種識別置信度
+            combined_confidence = detection_confidence * top1_prob
+
+            if combined_confidence >= 0.4:
                 breed = topk_breeds[0]
                 description = get_dog_description(breed)
                 formatted_description = format_description(description, breed)
                 explanations.append(f"Dog {i+1}: {formatted_description}")
-            elif top1_prob >= 0.2:
+            elif combined_confidence >= 0.2:
                 dog_explanation = f"Dog {i+1}: Top 3 possible breeds:\n"
                 dog_explanation += "\n".join([f"{j+1}. **{breed}** ({prob} confidence)" for j, (breed, prob) in enumerate(zip(topk_breeds[:3], topk_probs_percent[:3]))])
                 explanations.append(dog_explanation)
                 buttons.extend([f"Dog {i+1}: More about {breed}" for breed in topk_breeds[:3]])
             else:
-                if len(dogs) == 1:
-                    explanations.append("The image is unclear or does not contain a recognized dog breed.")
-                else:
-                    explanations.append(f"Dog {i+1}: The image is unclear or the breed is not in the dataset.")
+                explanations.append(f"Dog {i+1}: The image is unclear or the breed is not in the dataset.")
 
         final_explanation = "\n\n".join(explanations)
         if buttons: