Merge pull request #28588 from abhishek-gola:ORT_GPU_wrapper

Added OnnxRuntime GPU wrapper #28588

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake

samples/dnn/openpose.py

@@ -82,7 +82,9 @@ while cv.waitKey(1) < 0:
     inp = cv.dnn.blobFromImage(frame, inScale, (inWidth, inHeight),
                               (0, 0, 0), swapRB=False, crop=False)
     net.setInput(inp)
+    t0 = cv.getTickCount()
     out = net.forward()
+    t = (cv.getTickCount() - t0) / cv.getTickFrequency()
 
     assert(len(BODY_PARTS) <= out.shape[1])
 
@@ -115,8 +117,6 @@ while cv.waitKey(1) < 0:
             cv.ellipse(frame, points[idFrom], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)
             cv.ellipse(frame, points[idTo], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)
 
-    t, _ = net.getPerfProfile()
-    freq = cv.getTickFrequency() / 1000
-    cv.putText(frame, '%.2fms' % (t / freq), (10, 20), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))
+    cv.putText(frame, '%.2f ms' % (t * 1000.0), (10, 20), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))
 
     cv.imshow('OpenPose using OpenCV', frame)