diff --git a/examples/vision/detection/yolov5/quantize/cpp/README.md b/examples/vision/detection/yolov5/quantize/cpp/README.md
index 2555cee21..90334c7ba 100644
--- a/examples/vision/detection/yolov5/quantize/cpp/README.md
+++ b/examples/vision/detection/yolov5/quantize/cpp/README.md
@@ -28,7 +28,7 @@ tar -xvf yolov5s_quant.tar
 wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
 
 
-# 在CPU上使用Paddle-Inference推理量化模型
+# 在CPU上使用ONNX Runtime推理量化模型
 ./infer_demo yolov5s_quant 000000014439.jpg 0
 # 在GPU上使用TensorRT推理量化模型
 ./infer_demo yolov5s_quant 000000014439.jpg 1
diff --git a/examples/vision/detection/yolov5/quantize/cpp/infer.cc b/examples/vision/detection/yolov5/quantize/cpp/infer.cc
index 54e9d6dc1..e429b2aad 100644
--- a/examples/vision/detection/yolov5/quantize/cpp/infer.cc
+++ b/examples/vision/detection/yolov5/quantize/cpp/infer.cc
@@ -64,7 +64,7 @@ int main(int argc, char* argv[]) {
 
   if (flag == 0) {
     option.UseCpu();
-    option.UsePaddleBackend();
+    option.UseOrtBackend();
   } else if (flag == 1) {
     option.UseGpu();
     option.UseTrtBackend();
diff --git a/examples/vision/detection/yolov5/quantize/python/README.md b/examples/vision/detection/yolov5/quantize/python/README.md
index 28086d8b5..c63ef712c 100644
--- a/examples/vision/detection/yolov5/quantize/python/README.md
+++ b/examples/vision/detection/yolov5/quantize/python/README.md
@@ -22,8 +22,8 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar
 tar -xvf yolov5s_quant.tar
 wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
 
-# 在CPU上使用Paddle-Inference推理量化模型
-python infer.py --model yolov5s_quant --image 000000014439.jpg --device cpu --backend paddle
+# 在CPU上使用ONNX Runtime推理量化模型
+python infer.py --model yolov5s_quant --image 000000014439.jpg --device cpu --backend ort
 # 在GPU上使用TensorRT推理量化模型
 python infer.py --model yolov5s_quant --image 000000014439.jpg --device gpu --backend trt
 # 在GPU上使用Paddle-TensorRT推理量化模型
diff --git a/examples/vision/detection/yolov5/quantize/python/infer.py b/examples/vision/detection/yolov5/quantize/python/infer.py
index 2e420c360..da502fe93 100644
--- a/examples/vision/detection/yolov5/quantize/python/infer.py
+++ b/examples/vision/detection/yolov5/quantize/python/infer.py
@@ -54,12 +54,6 @@ def build_option(args):
         option.enable_paddle_to_trt()
     elif args.backend.lower() == "ort":
         option.use_ort_backend()
-    elif args.backend.lower() == "paddle":
-        option.use_paddle_backend()
-    elif args.backend.lower() == "openvino":
-        assert args.device.lower(
-        ) == "cpu", "OpenVINO backend require inference on device CPU."
-        option.use_openvino_backend()
     return option
 
 
diff --git a/examples/vision/detection/yolov6/quantize/cpp/README.md b/examples/vision/detection/yolov6/quantize/cpp/README.md
index 5859b7de1..ee11f315d 100644
--- a/examples/vision/detection/yolov6/quantize/cpp/README.md
+++ b/examples/vision/detection/yolov6/quantize/cpp/README.md
@@ -28,7 +28,7 @@ tar -xvf yolov6s_qat_model.tar
 wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
 
 
-# 在CPU上使用Paddle-Inference推理量化模型
+# 在CPU上使用ONNX Runtime推理量化模型
 ./infer_demo yolov6s_qat_model 000000014439.jpg 0
 # 在GPU上使用TensorRT推理量化模型
 ./infer_demo yolov6s_qat_model 000000014439.jpg 1
diff --git a/examples/vision/detection/yolov6/quantize/cpp/infer.cc b/examples/vision/detection/yolov6/quantize/cpp/infer.cc
index 64f4d9f22..b40200962 100644
--- a/examples/vision/detection/yolov6/quantize/cpp/infer.cc
+++ b/examples/vision/detection/yolov6/quantize/cpp/infer.cc
@@ -64,7 +64,7 @@ int main(int argc, char* argv[]) {
 
   if (flag == 0) {
     option.UseCpu();
-    option.UsePaddleBackend();
+    option.UseOrtBackend();
   } else if (flag == 1) {
     option.UseGpu();
     option.UseTrtBackend();
diff --git a/examples/vision/detection/yolov6/quantize/python/README.md b/examples/vision/detection/yolov6/quantize/python/README.md
index 889fe2f11..169a0a946 100644
--- a/examples/vision/detection/yolov6/quantize/python/README.md
+++ b/examples/vision/detection/yolov6/quantize/python/README.md
@@ -21,8 +21,8 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_qat_model.tar
 tar -xvf yolov6s_qat_model.tar
 wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
 
-# 在CPU上使用Paddle-Inference推理量化模型
-python infer.py --model yolov6s_qat_model --image 000000014439.jpg --device cpu --backend paddle
+# 在CPU上使用ONNX Runtime推理量化模型
+python infer.py --model yolov6s_qat_model --image 000000014439.jpg --device cpu --backend ort
 # 在GPU上使用TensorRT推理量化模型
 python infer.py --model yolov6s_qat_model --image 000000014439.jpg --device gpu --backend trt
 # 在GPU上使用Paddle-TensorRT推理量化模型
diff --git a/examples/vision/detection/yolov6/quantize/python/infer.py b/examples/vision/detection/yolov6/quantize/python/infer.py
index d34c7cd59..da9fa3d97 100644
--- a/examples/vision/detection/yolov6/quantize/python/infer.py
+++ b/examples/vision/detection/yolov6/quantize/python/infer.py
@@ -54,12 +54,6 @@ def build_option(args):
         option.enable_paddle_to_trt()
     elif args.backend.lower() == "ort":
         option.use_ort_backend()
-    elif args.backend.lower() == "paddle":
-        option.use_paddle_backend()
-    elif args.backend.lower() == "openvino":
-        assert args.device.lower(
-        ) == "cpu", "OpenVINO backend require inference on device CPU."
-        option.use_openvino_backend()
     return option
 
 
diff --git a/examples/vision/detection/yolov7/quantize/cpp/README.md b/examples/vision/detection/yolov7/quantize/cpp/README.md
index bf676253a..17eb9eb0f 100644
--- a/examples/vision/detection/yolov7/quantize/cpp/README.md
+++ b/examples/vision/detection/yolov7/quantize/cpp/README.md
@@ -28,7 +28,7 @@ tar -xvf yolov7_quant.tar
 wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
 
 
-# 在CPU上使用Paddle-Inference推理量化模型
+# 在CPU上使用ONNX Runtime推理量化模型
 ./infer_demo yolov7_quant 000000014439.jpg 0
 # 在GPU上使用TensorRT推理量化模型
 ./infer_demo yolov7_quant 000000014439.jpg 1
diff --git a/examples/vision/detection/yolov7/quantize/cpp/infer.cc b/examples/vision/detection/yolov7/quantize/cpp/infer.cc
index 8a656adee..0eda80b6c 100644
--- a/examples/vision/detection/yolov7/quantize/cpp/infer.cc
+++ b/examples/vision/detection/yolov7/quantize/cpp/infer.cc
@@ -64,7 +64,7 @@ int main(int argc, char* argv[]) {
 
   if (flag == 0) {
     option.UseCpu();
-    option.UsePaddleBackend();
+    option.UseOrtBackend();
   } else if (flag == 1) {
     option.UseGpu();
     option.UseTrtBackend();
diff --git a/examples/vision/detection/yolov7/quantize/python/README.md b/examples/vision/detection/yolov7/quantize/python/README.md
index e82dc4615..4389d44c1 100644
--- a/examples/vision/detection/yolov7/quantize/python/README.md
+++ b/examples/vision/detection/yolov7/quantize/python/README.md
@@ -21,8 +21,8 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar
 tar -xvf yolov7_quant.tar
 wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
 
-# 在CPU上使用Paddle-Inference推理量化模型
-python infer.py --model yolov7_quant --image 000000014439.jpg --device cpu --backend paddle
+# 在CPU上使用ONNX Runtime推理量化模型
+python infer.py --model yolov7_quant --image 000000014439.jpg --device cpu --backend ort
 # 在GPU上使用TensorRT推理量化模型
 python infer.py --model yolov7_quant --image 000000014439.jpg --device gpu --backend trt
 # 在GPU上使用Paddle-TensorRT推理量化模型
diff --git a/examples/vision/detection/yolov7/quantize/python/infer.py b/examples/vision/detection/yolov7/quantize/python/infer.py
index 4790a4d94..de84e4061 100644
--- a/examples/vision/detection/yolov7/quantize/python/infer.py
+++ b/examples/vision/detection/yolov7/quantize/python/infer.py
@@ -54,12 +54,6 @@ def build_option(args):
         option.enable_paddle_to_trt()
     elif args.backend.lower() == "ort":
         option.use_ort_backend()
-    elif args.backend.lower() == "paddle":
-        option.use_paddle_backend()
-    elif args.backend.lower() == "openvino":
-        assert args.device.lower(
-        ) == "cpu", "OpenVINO backend require inference on device CPU."
-        option.use_openvino_backend()
     return option
 
 
diff --git a/python/fastdeploy/vision/detection/contrib/yolov5.py b/python/fastdeploy/vision/detection/contrib/yolov5.py
index b8113f3b8..7d87d6e42 100644
--- a/python/fastdeploy/vision/detection/contrib/yolov5.py
+++ b/python/fastdeploy/vision/detection/contrib/yolov5.py
@@ -151,7 +151,6 @@ class YOLOv5(FastDeployModel):
         # 初始化后的option保存在self._runtime_option
         super(YOLOv5, self).__init__(runtime_option)
 
-        assert model_format == ModelFormat.ONNX, "YOLOv5 only support model format of ModelFormat.ONNX now."
         self._model = C.vision.detection.YOLOv5(
             model_file, params_file, self._runtime_option, model_format)
         # 通过self.initialized判断整个模型的初始化是否成功
diff --git a/python/fastdeploy/vision/detection/contrib/yolov7.py b/python/fastdeploy/vision/detection/contrib/yolov7.py
index 510b72ed6..1e4ddf7f6 100644
--- a/python/fastdeploy/vision/detection/contrib/yolov7.py
+++ b/python/fastdeploy/vision/detection/contrib/yolov7.py
@@ -137,7 +137,6 @@ class YOLOv7(FastDeployModel):
         # 初始化后的option保存在self._runtime_option
         super(YOLOv7, self).__init__(runtime_option)
 
-        assert model_format == ModelFormat.ONNX, "YOLOv7 only support model format of ModelFormat.ONNX now."
         self._model = C.vision.detection.YOLOv7(
             model_file, params_file, self._runtime_option, model_format)
         # 通过self.initialized判断整个模型的初始化是否成功