Update app.py

app.py

@@ -192,6 +192,7 @@ async def predict_single_dog(image):
         topk_breeds = [dog_breeds[idx.item()] for idx in topk_indices[0]]
         topk_probs_percent = [f"{prob.item() * 100:.2f}%" for prob in topk_probs[0]]
     return top1_prob, topk_breeds, topk_probs_percent
+    
 
 async def detect_multiple_dogs(image, conf_threshold=0.2, iou_threshold=0.45):
     results = model_yolo(image, conf=conf_threshold, iou=iou_threshold)[0]
@@ -207,8 +208,8 @@ async def detect_multiple_dogs(image, conf_threshold=0.2, iou_threshold=0.45):
     if not boxes:
         dogs.append((image, 1.0, [0, 0, image.width, image.height]))
     else:
-        # 按置信度排序並選擇前4個框（如果有的話）
-        sorted_boxes = sorted(boxes, key=lambda x: x[1], reverse=True)[:4]
+        # 按置信度排序並選擇所有框
+        sorted_boxes = sorted(boxes, key=lambda x: x[1], reverse=True)
         
         for box, confidence in sorted_boxes:
             x1, y1, x2, y2 = box
@@ -223,41 +224,6 @@ async def detect_multiple_dogs(image, conf_threshold=0.2, iou_threshold=0.45):
 
     return dogs
 
-def merge_boxes(boxes, iou_threshold=0.5):
-    merged = []
-    while boxes:
-        base_box = boxes.pop(0)
-        i = 0
-        while i < len(boxes):
-            if calculate_iou(base_box[0], boxes[i][0]) > iou_threshold:
-                base_box = merge_two_boxes(base_box, boxes.pop(i))
-            else:
-                i += 1
-        merged.append(base_box)
-    return merged
-
-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
-
-def merge_two_boxes(box1, box2):
-    return (
-        [min(box1[0][0], box2[0][0]),
-         min(box1[0][1], box2[0][1]),
-         max(box1[0][2], box2[0][2]),
-         max(box1[0][3], box2[0][3])],
-        max(box1[1], box2[1])  # 取較高的置信度
-    )
-
 
 async def process_single_dog(image):
     top1_prob, topk_breeds, topk_probs_percent = await predict_single_dog(image)
@@ -456,6 +422,70 @@ 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:
         return "Please upload an image to start.", None, gr.update(visible=False, choices=[]), None
@@ -490,7 +520,10 @@ async def predict(image):
                 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.")
+                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.")
 
         final_explanation = "\n\n".join(explanations)
         if buttons: