[Bug]: The OpenVINO model is unable to perform output value clamp using C++.

[Huairui]

OpenVINO Version

2025.0

Operating System

Red Hat Enterprise Linux 8

Device used for inference

CPU

Framework

PyTorch

Model used

No response

Issue description

I create a PyTorch model and convert it to an OpenVINO model using the Python script. Then I test the model performance in a Python environment, and everything goes well. But when I use the model in C++, the clamp operation fails to work.
For example, I use the OpenVINO SR model to process 10-bit videos, where the input pixel value range is 0-1023, but the output value range is 0-65535, even though I place the clamp operation at the end. The problem is hard to meet because most of the time, we process 8-bit videos. The uint8 variable type will automatically clamp the output. When it comes to 10-bit content, the bug appears.

Step-by-step reproduction

No response

Relevant log output

Issue submission checklist

• I'm reporting an issue. It's not a question.
• I checked the problem with the documentation, FAQ, open issues, Stack Overflow, etc., and have not found a solution.
• There is reproducer code and related data files such as images, videos, models, etc.

[aviralgarg05]

I would like to solve this issue