Image normalization in deepstream pipeline

[young2theMax]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson AGX Orin
• DeepStream Version 6.2
• JetPack Version (valid for Jetson only) 5.1
• TensorRT Version 8.5.1.1
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

I have a question about the image processing in the deepstream pipeline.

In image normalization in deepstream pipeline, as far as I understood,
Image input for PGIE = (Read image - offsets) * net-scale-factor
is how it works.

But I wonder if the read image is divided by 255 as default or not.
Since the model normalization is usually done after division by 255.

[yuweiw]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

The net-scale-factor is the factor of dividing. You also can add some log in our demo code for normalization, it’s open source.

sources\libs\nvdsinfer\nvdsinfer_context_impl.cpp
NvDsInferStatus InferPreprocessor::transform()