How to use model.pb with deepstream5.0

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hello,
I have trained fire detection.pb model using this tutorial PyLessons and i want to run this .pb model using deepstream 5.0 ,how it possible, please

Thanks.

Deepstream5.0

3

There are two solutions:

  1. convert the TF models to onnx and deploy in DS which will use gst-nvinfer(TensorRT) to do inference
    Reference:
    1.1 converting to onnx TensorRT/ONNX - eLinux.org
    1.2 deepstream doc : Gst-nvinfer — DeepStream 6.1.1 Release documentation

  2. deploy the TF models directly which will use gst-nvinferserver(Triton) to do inference
    ds doc: Gst-nvinferserver — DeepStream 6.1.1 Release documentation
    ds sample: sources/apps/sample_apps/deepstream-segmentation-test

4

thanks