fixed indentation

handler.py

@@ -8,41 +8,37 @@ class EndpointHandler():
     def __init__(self, path=""):
         # Preload all the elements you are going to need at inference.
         model_type = "vit_b"
-		# prefix = "/opt/ml/model"
-		model_path = "tf_model.h5"
-		# model_checkpoint_path = os.path.join(prefix, "sam_vit_h_4b8939.pth")
+        # prefix = "/opt/ml/model"
+        model_path = "tf_model.h5"
+        # model_checkpoint_path = os.path.join(prefix, "sam_vit_h_4b8939.pth")
 
-		sam = sam_model_registry[model_type](checkpoint=model_path)
-		predictor = SamPredictor(sam)
+        sam = sam_model_registry[model_type](checkpoint=model_path)
+        self.predictor = SamPredictor(sam)
 
     def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
         """
-       data args:
+        data args:
             inputs (:obj: `str` | `PIL.Image` | `np.array`)
             kwargs
-      Return:
+        Return:
             A :obj:`list` | `dict`: will be serialized and returned
         """
 
-		inputs = data.pop("inputs", data)
-		image_url = inputs.pop("imageUrl", none)
+        inputs = data.pop("inputs", data)
+        image_url = inputs.pop("imageUrl", None)
 
-		if not image_url:
-			return jsonify({"error": "image_url not provided"}), 400
+        if not image_url:
+            return jsonify({"error": "image_url not provided"}), 400
 
-		try:
-			response = requests.get(image_url)
-			response.raise_for_status()
-			image = response.content
-		except requests.RequestException as e:
-			return jsonify({"error": f"Error downloading image: {str(e)}"}), 500
+        try:
+            response = requests.get(image_url)
+            response.raise_for_status()
+            image = response.content
+        except requests.RequestException as e:
+            return jsonify({"error": f"Error downloading image: {str(e)}"}), 500
 
+        self.predictor.set_image(image)
 
-		predictor.set_image(image)
+        image_embedding = self.predictor.get_image_embedding().cpu().numpy().tolist()
 
-		image_embedding = predictor.get_image_embedding().cpu().numpy().toList()
-
-		return jsonify(image_embedding)
-
-        # pseudo
-        # self.model(input)
+        return jsonify(image_embedding)