Update app.py

app.py

@@ -171,25 +171,22 @@ def predict(image):
         return "Please upload an image to get started.", gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
 
     try:
-        # 檢查圖片是否是 numpy.ndarray，如果是則轉換為 PIL.Image
+        # 確保圖片轉換為 PIL.Image 格式
         if isinstance(image, np.ndarray):
             image = Image.fromarray(image)
 
         # 使用 YOLO 偵測狗
         results = model_yolo(image)
-        boxes = results[0].boxes  # 提取邊界框
+        boxes = results[0].boxes  # 提取 YOLO 偵測結果中的邊界框
 
         if len(boxes) == 0:
-            return "No dog detected in the image.", gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
+            return "The image is too unclear or the dog breed is not in the dataset. Please upload a clearer image of the dog.", gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
 
         explanations = []
         visible_buttons = []
 
         for i, box in enumerate(boxes):
-            # 提取每隻狗的區域
-            x1, y1, x2, y2 = map(int, box.xyxy[0])  # 使用 box.xyxy 來提取邊界框座標
-
-            # 裁剪出狗區域，確保 image 是 PIL.Image 格式
+            x1, y1, x2, y2 = map(int, box.xyxy[0])
             cropped_image = image.crop((x1, y1, x2, y2))
             image_tensor = preprocess_image(cropped_image)
 
@@ -204,34 +201,28 @@ def predict(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]]
 
-                # 根據信心分數進行判斷
+                # 高於 50% 信心的情況，直接返回詳細資訊，不顯示信心分數
                 if top1_prob >= 0.5:
                     breed = topk_breeds[0]
                     description = get_dog_description(breed)
-                    explanations.append(f"Detected a dog: **{breed}** with {topk_probs_percent[0]} confidence.")
-                elif 0.2 <= top1_prob < 0.5:
+                    return format_description(description, breed), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
+
+                # 信心低於 50% 的情況，返回前三個可能的品種，並顯示按鈕
+                else:
                     explanation = (
-                        f"Detected a dog with moderate confidence. Here are the top 3 possible breeds:\n"
+                        f"The model couldn't confidently identify the breed. Here are the top 3 possible breeds:\n"
                         f"1. **{topk_breeds[0]}** ({topk_probs_percent[0]} confidence)\n"
                         f"2. **{topk_breeds[1]}** ({topk_probs_percent[1]} confidence)\n"
                         f"3. **{topk_breeds[2]}** ({topk_probs_percent[2]} confidence)\n"
+                        "Click on a button to view more information about the breed."
                     )
-                    explanations.append(explanation)
-                    visible_buttons.extend([i+1 for _ in range(3)])
-                else:
-                    explanations.append("The image is too unclear or the breed is not in the dataset. Please upload a clearer image.")
-
-        # 處理不同情境的結果
-        if len(explanations) > 0:
-            final_explanation = "\n\n".join(explanations)
-            return final_explanation, gr.update(visible=len(visible_buttons) >= 1), gr.update(visible=len(visible_buttons) >= 2), gr.update(visible=len(visible_buttons) >= 3)
+                    return explanation, gr.update(visible=True, value=f"More about {topk_breeds[0]}"), gr.update(visible=True, value=f"More about {topk_breeds[1]}"), gr.update(visible=True, value=f"More about {topk_breeds[2]}")
 
     except Exception as e:
         return f"An error occurred: {e}", gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
 
 
 
-
 def format_description(description, breed):
     if isinstance(description, dict):
         formatted_description = "\n\n".join([f"**{key}**: {value}" for key, value in description.items()])