[Benchmark]Compare diff for OCR (#1415)

* avoid mem copy for cpp benchmark

* set CMAKE_BUILD_TYPE to Release

* Add SegmentationDiff

* change pointer to reference

* fixed bug

* cast uint8 to int32

* Add diff compare for OCR

* Add diff compare for OCR

* rm ppocr pipeline

* Add yolov5 diff compare

* Add yolov5 diff compare

* deal with comments

* deal with comments

* fixed bug

* fixed bug

fastdeploy/vision/detection/contrib/yolov8/preprocessor.cc

@@ -83,7 +83,7 @@ bool YOLOv8Preprocessor::Preprocess(
                                 static_cast<float>(mat->Width())};
 
   mat->ShareWithTensor(output);
-  output->ExpandDim(0);  // reshape to n, h, w, c
+  output->ExpandDim(0);  // reshape to n, c, h, w
   return true;
 }