Update app.py

app.py

@@ -153,33 +153,6 @@ def format_description(description, breed):
 
     return formatted_description
 
-# async def predict_single_dog(image):
-#     return await asyncio.to_thread(_predict_single_dog, image)
-
-# def _predict_single_dog(image):
-#     image_tensor = preprocess_image(image)
-#     with torch.no_grad():
-#         output = model(image_tensor)
-#         logits = output[0] if isinstance(output, tuple) else output
-#         probabilities = F.softmax(logits, dim=1)
-#         topk_probs, topk_indices = torch.topk(probabilities, k=3)
-#         top1_prob = topk_probs[0][0].item()
-#         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=0.25, iou_threshold=0.4):
-#     results = model_yolo(image, conf=conf_threshold, iou=iou_threshold)[0]
-#     dogs = []
-#     for box in results.boxes:
-#         if box.cls == 16:  # COCO 資料集中狗的類別是 16
-#             xyxy = box.xyxy[0].tolist()
-#             confidence = box.conf.item()
-#             cropped_image = image.crop((xyxy[0], xyxy[1], xyxy[2], xyxy[3]))
-#             dogs.append((cropped_image, confidence, xyxy))
-#     return dogs
-
 
 async def predict_single_dog(image):
     image_tensor = preprocess_image(image)
@@ -194,6 +167,33 @@ 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):
+#     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
+
 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 = []
@@ -212,13 +212,17 @@ async def detect_multiple_dogs(image, conf_threshold=0.25, iou_threshold=0.4):
         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)
+            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]))
     
+    # 如果只检测到一只狗，但置信度较低，添加整张图片作为备选
+    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):
@@ -291,16 +295,16 @@ async def process_single_dog(image):
         }
         return explanation, image, buttons[0], buttons[1], buttons[2], gr.update(visible=True), initial_state
 
+
 # async def predict(image):
 #     if image is None:
-#         return "Please upload an image to start.", None, gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), 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, conf_threshold=0.25, iou_threshold=0.4)
-        
-#         if len(dogs) <= 1:
-#             return await process_single_dog(image)
+
+#         dogs = await detect_multiple_dogs(image)
         
 #         color_list = ['#FF0000', '#00FF00', '#0000FF', '#FFFF00', '#00FFFF', '#FF00FF', '#800080', '#FFA500']
 #         explanations = []
@@ -308,26 +312,28 @@ async def process_single_dog(image):
 #         annotated_image = image.copy()
 #         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)
-            
-#             breed = topk_breeds[0]
+
+#             combined_confidence = detection_confidence * top1_prob
+
 #             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:
+#             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([gr.update(visible=True, value=f"Dog {i+1}: More about {breed}") for breed in topk_breeds[:3]])
+#                 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.")
-        
+#                 explanations.append(f"Dog {i+1}: The image is unclear or the breed is not in the dataset. Please upload a clearer image.")
+
 #         final_explanation = "\n\n".join(explanations)
 #         if buttons:
 #             final_explanation += "\n\nClick on a button to view more information about the breed."
@@ -336,111 +342,25 @@ async def process_single_dog(image):
 #                 "buttons": buttons,
 #                 "show_back": True,
 #                 "image": annotated_image,
-#                 "is_multi_dog": True,
+#                 "is_multi_dog": len(dogs) > 1,
 #                 "dogs_info": explanations
 #             }
-#             return (final_explanation, annotated_image, 
-#                     buttons[0] if len(buttons) > 0 else gr.update(visible=False),
-#                     buttons[1] if len(buttons) > 1 else gr.update(visible=False),
-#                     buttons[2] if len(buttons) > 2 else gr.update(visible=False),
-#                     gr.update(visible=True),
-#                     initial_state)
+#             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": True,
+#                 "is_multi_dog": len(dogs) > 1,
 #                 "dogs_info": explanations
 #             }
-#             return final_explanation, annotated_image, gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), initial_state
-#     except Exception as e:
-#         error_msg = f"An error occurred: {str(e)}"
-#         print(error_msg)  # 添加日誌輸出
-#         return error_msg, None, gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), None
-
+#             return final_explanation, annotated_image, gr.update(visible=False, choices=[]), initial_state
 
-# def show_details(choice, previous_output, initial_state):
-#     if not choice:
-#         return previous_output, gr.update(visible=True), initial_state
-
-#     try:
-#         breed = choice.split("More about ")[-1]
-#         description = get_dog_description(breed)
-#         formatted_description = format_description(description, breed)
-        
-#         # 保存當前描述和原始按鈕狀態
-#         initial_state["current_description"] = formatted_description
-#         initial_state["original_buttons"] = initial_state.get("buttons", [])
-        
-#         return formatted_description, gr.update(visible=True), initial_state
 #     except Exception as e:
-#         error_msg = f"An error occurred while showing details: {e}"
+#         error_msg = f"An error occurred: {str(e)}\n\nTraceback:\n{traceback.format_exc()}"
 #         print(error_msg)
-#         return error_msg, gr.update(visible=True), initial_state
-
-# def go_back(state):
-#     buttons = state.get("buttons", [])
-#     return (
-#         state["explanation"],
-#         state["image"],
-#         buttons[0] if len(buttons) > 0 else gr.update(visible=False),
-#         buttons[1] if len(buttons) > 1 else gr.update(visible=False),
-#         buttons[2] if len(buttons) > 2 else gr.update(visible=False),
-#         gr.update(visible=False),  # 隱藏 back 按鈕
-#         state
-#     )
-
-# with gr.Blocks() as iface:
-#     gr.HTML("<h1 style='text-align: center;'>🐶 Dog Breed Classifier 🔍</h1>")
-#     gr.HTML("<p style='text-align: center;'>Upload a picture of a dog, and the model will predict its breed, provide detailed information, and include an extra information link!</p>")
-    
-#     with gr.Row():
-#         input_image = gr.Image(label="Upload a dog image", type="pil")
-#         output_image = gr.Image(label="Annotated Image")
-    
-#     output = gr.Markdown(label="Prediction Results")
-    
-#     with gr.Row():
-#         btn1 = gr.Button("View More 1", visible=False)
-#         btn2 = gr.Button("View More 2", visible=False)
-#         btn3 = gr.Button("View More 3", visible=False)
-    
-#     back_button = gr.Button("Back", visible=False)
-    
-#     initial_state = gr.State()
-    
-#     input_image.change(
-#         predict,
-#         inputs=input_image,
-#         outputs=[output, output_image, btn1, btn2, btn3, back_button, initial_state]
-#     )
-
-#     for btn in [btn1, btn2, btn3]:
-#         btn.click(
-#             show_details,
-#             inputs=[btn, output, initial_state],
-#             outputs=[output, back_button, initial_state]
-#         )
-
-#     back_button.click(
-#         go_back,
-#         inputs=[initial_state],
-#         outputs=[output, output_image, btn1, btn2, btn3, back_button, initial_state]
-#     )
-
-#     gr.Examples(
-#         examples=['Border_Collie.jpg', 'Golden_Retriever.jpeg', 'Saint_Bernard.jpeg', 'French_Bulldog.jpeg', 'Samoyed.jpg'],
-#         inputs=input_image
-#     )
-
-#     gr.HTML('For more details on this project and other work, feel free to visit my GitHub <a href="https://github.com/Eric-Chung-0511/Learning-Record/tree/main/Data%20Science%20Projects/Dog_Breed_Classifier">Dog Breed Classifier</a>')
-
-# if __name__ == "__main__":
-#     iface.launch()
-
-
+#         return error_msg, None, gr.update(visible=False, choices=[]), None
 
 async def predict(image):
     if image is None:
@@ -463,7 +383,9 @@ async def predict(image):
             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 len(dogs) > 1:
+                draw.text((box[0], box[1]), f"Dog {i+1}", fill=color, font=font)
 
             combined_confidence = detection_confidence * top1_prob
 
@@ -471,14 +393,23 @@ async def predict(image):
                 breed = topk_breeds[0]
                 description = get_dog_description(breed)
                 formatted_description = format_description(description, breed)
-                explanations.append(f"Dog {i+1}: {formatted_description}")
+                if len(dogs) == 1:
+                    explanations.append(f"Breed: {breed}\n{formatted_description}")
+                else:
+                    explanations.append(f"Dog {i+1}: Breed: {breed}\n{formatted_description}")
             elif combined_confidence >= 0.2:
-                dog_explanation = f"Dog {i+1}: Top 3 possible breeds:\n"
+                if len(dogs) == 1:
+                    dog_explanation = f"Top 3 possible breeds:\n"
+                else:
+                    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]])
+                buttons.extend([f"{'Dog ' + str(i+1) + ': ' if len(dogs) > 1 else ''}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. Please upload a clearer image.")
+                if len(dogs) == 1:
+                    explanations.append("The image is unclear or the breed is not in the dataset. Please upload a clearer image.")
+                else:
+                    explanations.append(f"Dog {i+1}: The image is unclear or the breed is not in the dataset. Please upload a clearer image.")
 
         final_explanation = "\n\n".join(explanations)
         if buttons: