Peh Yu Chern

Please ensure that you're using the same benchmark parameters when comparing the performance between two different versions of benchmark_app. For example, `-nireq, -nstreams, -nthreads` If the scenario is still the...

Could you share your relevant model files?

Can you check with the latest 2024.1 release to see whether it has the same issue?

Closing issue, feel free to re-open or start a new issue if additional assistance is needed.

The code is shared in #24288 . Sharing the code here. `import numpy as np import onnx from onnx import helper from onnx import AttributeProto, TensorProto, GraphProto index = [1,...