Merge pull request #28752 from abhishek-gola:net_profiling

Added net profiling support #28752

### 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/object_detection.py

@@ -71,6 +71,7 @@ if args.alias is None or hasattr(args, 'help'):
     help()
     exit(1)
 
+cv.utils.logging.setLogLevel(cv.utils.logging.LOG_LEVEL_INFO)
 args.model = findModel(args.model, args.sha1)
 if args.config is not None:
     args.config = findModel(args.config, args.config_sha1)
@@ -104,6 +105,8 @@ if args.backend != "default" or args.target != "cpu":
 net = cv.dnn.readNet(args.model, args.config, "", engine)
 net.setPreferableBackend(get_backend_id(args.backend))
 net.setPreferableTarget(get_target_id(args.target))
+if hasattr(cv.dnn, 'DNN_PROFILE_SUMMARY'):
+    net.setProfilingMode(cv.dnn.DNN_PROFILE_SUMMARY)
 outNames = net.getUnconnectedOutLayersNames()
 
 confThreshold = args.thr
@@ -340,6 +343,7 @@ def processingThreadBody():
                 futureOutputs.append(net.forwardAsync())
             else:
                 outs = net.forward(outNames)
+                net.printPerfProfile()
                 predictionsQueue.put(copy.deepcopy(outs))
 
         while futureOutputs and futureOutputs[0].wait_for(0):
@@ -408,6 +412,7 @@ else:
 
         net.setInput(blob)
         outs = net.forward(outNames)
+        net.printPerfProfile()
 
         boxes, classIds, confidences, indices = postprocess(frame, outs)
         drawPred(classIds, confidences, boxes, indices, (stdSize*max(frame.shape[:2]))/stdImgSize, (stdWeight*max(frame.shape[:2]))//stdImgSize)