Where is preprocessing_mode

Please provide the following information when requesting support.

• Hardware (RTX A6000)
• Network Type (Classification PyT)

I followed this tutorial Image Classification PyT to generate an ONNX model file, and then followed this tutorial Deploying to DeepStream for Classification TF1/TF2/PyTorch to deploy this model file to deepstream. I need to set several parameters ( net-scale-factor, offsets, and model-color-format) in the configuration file, but I don’t see these parameters in the model training script. Can you tell me where to find them?

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

Refer to https://github.com/NVIDIA/tao_tensorflow1_backend/blob/main/nvidia_tao_tf1/cv/makenet/utils/preprocess_input.py

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.