Mask Obtained from Deepstream are not same as TAO inferecing Output

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

@nitinp14920914 DeepStream is not just for any specific model. We don’t know anything about your model. So you may need to check whether the nvinfer configuration is correct or not. Maybe the nvinfer debug tips will be helpful for you. DeepStream SDK FAQ - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums

Can you refer to the C sample first? NVIDIA-AI-IOT/deepstream_tao_apps: Sample apps to demonstrate how to deploy models trained with TAO on DeepStream (github.com)