Update api_server.py

api_server.py

@@ -24,8 +24,8 @@ load_type = 'local'
 MODEL_YOLO = "yolo11_detect_best_241024_1.pt"
 MODEL_DIR = "./artifacts/models"
 YOLO_DIR = "./artifacts/yolo"
-GRADIO_URL = "https://be45c9b1bdbad4d28e.gradio.live/"
-#REPO_ID = "1vash/mnist_demo_model"
+GRADIO_URL = "https://fd39e54bcb191a37bf.gradio.live/"
+
 
 # Load the saved YOLO model into memory
 if load_type == 'local':
@@ -98,10 +98,6 @@ check_memory_usage()
 
 # Initialize the Flask application
 app = Flask(__name__)
-# # Initialize the ClipModel at the start
-# clip_model = ClipModel()
-
-
 
 # API route for prediction(YOLO)
 @app.route('/predict', methods=['POST'])
@@ -114,7 +110,6 @@ def predict():
     if 'image' not in request.files:
         # Handle if no file is selected
         return jsonify({"error": "No image part"}), 400
-        #return 'No file selected'
 
     # 讀取圖像
     try:
@@ -177,17 +172,6 @@ def predict():
                 encoded_images.append(image_to_base64(yolo_img))
                 element_list.append(element)
                 print(f"===== CLIP result:{top_k_words} =====\n")
-
-            # if element_counts[element] > 1: #某隻角色的數量>1
-            #     yolo_path = f"{YOLO_DIR}/{message_id}/{element}"
-            #     yolo_file = get_jpg_files(yolo_path)
-
-            #     for yolo_img in yolo_file: # 取得每張圖的路徑
-            #         encoded_images.append(image_to_base64(yolo_img))
-
-            # else  : #某隻角色的數量=1
-            #     yolo_path = f"{YOLO_DIR}/{message_id}/{element}/im.jpg.jpg"
-            #     encoded_images.append(image_to_base64(yolo_path))
                 
         # 建立回應資料
         response_data = {
@@ -205,44 +189,7 @@ def predict():
             ]
         }
         
-        return jsonify(response_data), 200 #jsonify(response_data)
-            
-        # for label_name in label_names:
-        #     yolo_file=f"{YOLO_DIR}/{message_id}/{label_name}/im.jpg.jpg"
-        #     # 將圖片轉換為 base64 編碼
-        #     encoded_images.append(image_to_base64(yolo_file))
-
-    
-    # # dictionary is not a JSON: https://www.quora.com/What-is-the-difference-between-JSON-and-a-dictionary
-    # # flask.jsonify vs json.dumps https://sentry.io/answers/difference-between-json-dumps-and-flask-jsonify/
-    # # The flask.jsonify() function returns a Response object with Serializable JSON and content_type=application/json.
-    # return jsonify(response)
-
-
-# # Helper function to preprocess the image
-# def preprocess_image(image_data):
-#     """Preprocess image for YOLO Model Inference
-
-#     :param image_data: Raw image (PIL.Image)
-#     :return: image: Preprocessed Image (Tensor)
-#     """
-#     # Define the YOLO input size (example 640x640, you can modify this based on your model)
-#     input_size = (640, 640)
-
-#     # Define transformation: Resize the image, convert to Tensor, and normalize pixel values
-#     transform = transforms.Compose([
-#         transforms.Resize(input_size),       # Resize to YOLO input size
-#         transforms.ToTensor(),               # Convert image to PyTorch Tensor (通道數、影像高度和寬度)
-#         transforms.Normalize([0.0, 0.0, 0.0], [1.0, 1.0, 1.0])  # Normalization (if needed)
-#     ])
-
-#     # Apply transformations to the image
-#     image = transform(image_data)
-
-#     # Add batch dimension (1, C, H, W) since YOLO expects a batch
-#     image = image.unsqueeze(0)
-
-#     return image
+        return jsonify(response_data), 200 
 
 
 # API route for health check