edited readme

efficientdet-d0/README.md

@@ -33,8 +33,7 @@ net = cv2.dnn.readNet("efficientdet-d0_2026jul.onnx")
 ```
 
 ### C++
-The C++ demo runs inference with OpenCV's DNN module (default engine — no ONNX Runtime
-needed). Adjust the OpenCV paths to your setup:
+The C++ demo runs inference with OpenCV's DNN module. Adjust the OpenCV paths to your setup:
 ```bash
 OCV=/path/to/opencv                          # OpenCV source tree
 OCVBUILD=/path/to/opencv/build               # OpenCV build directory (generated headers + libs)

faster_rcnn_inception_v2_coco_2018_01_28/README.md

@@ -3,7 +3,7 @@
 Object detection with the Faster-RCNN meta-architecture and an Inception v2 backbone,
 trained on the COCO dataset. The model was originally distributed as a frozen TensorFlow
 graph (`faster_rcnn_inception_v2_coco_2018_01_28.pb`) from the TensorFlow Object Detection
-API and converted to ONNX for inference with OpenCV's DNN module (ONNX Runtime engine).
+API and converted to ONNX for inference with OpenCV's DNN module.
 
 ## Model Details
 - **Architecture**: Faster-RCNN with an Inception v2 backbone
@@ -20,12 +20,10 @@ python demo.py --model faster_rcnn_inception_v2_coco_2018_01_28_2026jul.onnx --i
 ```
 
 ### C++
-The C++ demo runs inference with OpenCV's DNN module using its ONNX Runtime engine
-(`ENGINE_ORT`), so OpenCV must be built with `-DWITH_ONNXRUNTIME=ON`. Adjust the OpenCV
-paths to your setup:
+The C++ demo runs inference with OpenCV's DNN module. Adjust the OpenCV paths to your setup:
 ```bash
 OCV=/path/to/opencv                          # OpenCV source tree
-OCVBUILD=/path/to/opencv/build               # OpenCV build directory (built with -DWITH_ONNXRUNTIME=ON)
+OCVBUILD=/path/to/opencv/build               # OpenCV build directory (generated headers + libs)
 g++ -std=c++17 demo.cpp -o demo \
   -I$OCV/include \
   -I$OCV/modules/core/include \

faster_rcnn_resnet50_coco_2018_01_28/README.md

@@ -3,7 +3,7 @@
 Object detection with the Faster-RCNN meta-architecture and a ResNet-50 backbone,
 trained on the COCO dataset. The model was originally distributed as a frozen TensorFlow
 graph (`faster_rcnn_resnet50_coco_2018_01_28.pb`) from the TensorFlow Object Detection
-API and converted to ONNX for inference with OpenCV's DNN module (ONNX Runtime engine).
+API and converted to ONNX for inference with OpenCV's DNN module.
 
 ## Model Details
 - **Architecture**: Faster-RCNN with a ResNet-50 backbone
@@ -20,12 +20,10 @@ python demo.py --model faster_rcnn_resnet50_coco_2018_01_28_2026jul.onnx --image
 ```
 
 ### C++
-The C++ demo runs inference with OpenCV's DNN module using its ONNX Runtime engine
-(`ENGINE_ORT`), so OpenCV must be built with `-DWITH_ONNXRUNTIME=ON`. Adjust the OpenCV
-paths to your setup:
+The C++ demo runs inference with OpenCV's DNN module. Adjust the OpenCV paths to your setup:
 ```bash
 OCV=/path/to/opencv                          # OpenCV source tree
-OCVBUILD=/path/to/opencv/build               # OpenCV build directory (built with -DWITH_ONNXRUNTIME=ON)
+OCVBUILD=/path/to/opencv/build               # OpenCV build directory (generated headers + libs)
 g++ -std=c++17 demo.cpp -o demo \
   -I$OCV/include \
   -I$OCV/modules/core/include \

mask_rcnn_inception_v2_coco_2018_01_28/README.md

@@ -3,7 +3,7 @@
 Instance segmentation with the Mask-RCNN Inception v2 network trained on the COCO dataset.
 The model was originally distributed as a frozen TensorFlow graph
 (`mask_rcnn_inception_v2_coco_2018_01_28.pb`) from the TensorFlow Object Detection API
-and converted to ONNX for use with OpenCV's DNN module (ONNX Runtime engine).
+and converted to ONNX for use with OpenCV's DNN module.
 
 ## Model Details
 - **Architecture**: Mask-RCNN with an Inception v2 backbone
@@ -22,12 +22,10 @@ python demo.py --model mask_rcnn_inception_v2_coco_2018_01_28_2026jul.onnx --ima
 ```
 
 ### C++
-The C++ demo runs inference with OpenCV's DNN module using its ONNX Runtime engine
-(`ENGINE_ORT`), so OpenCV must be built with `-DWITH_ONNXRUNTIME=ON`. Adjust the OpenCV
-paths to your setup:
+The C++ demo runs inference with OpenCV's DNN module. Adjust the OpenCV paths to your setup:
 ```bash
 OCV=/path/to/opencv                          # OpenCV source tree
-OCVBUILD=/path/to/opencv/build               # OpenCV build directory (built with -DWITH_ONNXRUNTIME=ON)
+OCVBUILD=/path/to/opencv/build               # OpenCV build directory (generated headers + libs)
 g++ -std=c++17 demo.cpp -o demo \
   -I$OCV/include \
   -I$OCV/modules/core/include \

opencv_face_detector_uint8/README.md

@@ -36,8 +36,7 @@ net = cv2.dnn.readNet("opencv_face_detector_uint8_2026jul.onnx")
 ```
 
 ### C++
-The C++ demo runs inference with OpenCV's DNN module (default engine — no ONNX Runtime
-needed). Adjust the OpenCV paths to your setup:
+The C++ demo runs inference with OpenCV's DNN module. Adjust the OpenCV paths to your setup:
 ```bash
 OCV=/path/to/opencv                          # OpenCV source tree
 OCVBUILD=/path/to/opencv/build               # OpenCV build directory (generated headers + libs)

ssd_inception_v2_coco_2017_11_17/README.md

@@ -19,12 +19,10 @@ python demo.py --model ssd_inception_v2_coco_2017_11_17_2026jul.onnx --image exa
 ```
 
 ### C++
-The C++ demo runs inference with OpenCV's DNN module using its ONNX Runtime engine
-(`ENGINE_ORT`), so OpenCV must be built with `-DWITH_ONNXRUNTIME=ON`. Adjust the OpenCV
-paths to your setup:
+The C++ demo runs inference with OpenCV's DNN module. Adjust the OpenCV paths to your setup:
 ```bash
 OCV=/path/to/opencv                          # OpenCV source tree
-OCVBUILD=/path/to/opencv/build               # OpenCV build directory (built with -DWITH_ONNXRUNTIME=ON)
+OCVBUILD=/path/to/opencv/build               # OpenCV build directory (generated headers + libs)
 g++ -std=c++17 demo.cpp -o demo \
   -I$OCV/include \
   -I$OCV/modules/core/include \

ssd_mobilenet_v1_coco_2017_11_17/README.md

@@ -19,12 +19,10 @@ python demo.py --model ssd_mobilenet_v1_coco_2017_11_17_2026jul.onnx --image exa
 ```
 
 ### C++
-The C++ demo runs inference with OpenCV's DNN module using its ONNX Runtime engine
-(`ENGINE_ORT`), so OpenCV must be built with `-DWITH_ONNXRUNTIME=ON`. Adjust the OpenCV
-paths to your setup:
+The C++ demo runs inference with OpenCV's DNN module. Adjust the OpenCV paths to your setup:
 ```bash
 OCV=/path/to/opencv                          # OpenCV source tree
-OCVBUILD=/path/to/opencv/build               # OpenCV build directory (built with -DWITH_ONNXRUNTIME=ON)
+OCVBUILD=/path/to/opencv/build               # OpenCV build directory (generated headers + libs)
 g++ -std=c++17 demo.cpp -o demo \
   -I$OCV/include \
   -I$OCV/modules/core/include \

ssd_mobilenet_v1_ppn_coco/README.md

@@ -20,12 +20,10 @@ python demo.py --model ssd_mobilenet_v1_ppn_coco_2026jul.onnx --image example_ou
 ```
 
 ### C++
-The C++ demo runs inference with OpenCV's DNN module using its ONNX Runtime engine
-(`ENGINE_ORT`), so OpenCV must be built with `-DWITH_ONNXRUNTIME=ON`. Adjust the OpenCV
-paths to your setup:
+The C++ demo runs inference with OpenCV's DNN module. Adjust the OpenCV paths to your setup:
 ```bash
 OCV=/path/to/opencv                          # OpenCV source tree
-OCVBUILD=/path/to/opencv/build               # OpenCV build directory (built with -DWITH_ONNXRUNTIME=ON)
+OCVBUILD=/path/to/opencv/build               # OpenCV build directory (generated headers + libs)
 g++ -std=c++17 demo.cpp -o demo \
   -I$OCV/include \
   -I$OCV/modules/core/include \

ssd_mobilenet_v2_coco_2018_03_29/README.md

@@ -19,12 +19,10 @@ python demo.py --model ssd_mobilenet_v2_coco_2018_03_29_2026jul.onnx --image exa
 ```
 
 ### C++
-The C++ demo runs inference with OpenCV's DNN module using its ONNX Runtime engine
-(`ENGINE_ORT`), so OpenCV must be built with `-DWITH_ONNXRUNTIME=ON`. Adjust the OpenCV
-paths to your setup:
+The C++ demo runs inference with OpenCV's DNN module. Adjust the OpenCV paths to your setup:
 ```bash
 OCV=/path/to/opencv                          # OpenCV source tree
-OCVBUILD=/path/to/opencv/build               # OpenCV build directory (built with -DWITH_ONNXRUNTIME=ON)
+OCVBUILD=/path/to/opencv/build               # OpenCV build directory (generated headers + libs)
 g++ -std=c++17 demo.cpp -o demo \
   -I$OCV/include \
   -I$OCV/modules/core/include \

tensorflow_inception_graph/README.md

@@ -27,8 +27,7 @@ net = cv2.dnn.readNet("tensorflow_inception_graph_2026jul.onnx")
 ```
 
 ### C++
-The C++ demo runs inference with OpenCV's DNN module (default engine — no ONNX Runtime
-needed). Adjust the OpenCV paths to your setup:
+The C++ demo runs inference with OpenCV's DNN module. Adjust the OpenCV paths to your setup:
 ```bash
 OCV=/path/to/opencv                          # OpenCV source tree
 OCVBUILD=/path/to/opencv/build               # OpenCV build directory (generated headers + libs)