How to create a benchmark model for ssd_mobilenet_v2

[tatsu.ted_2059]

In the Jetson Nano benchmark (Jetson Benchmarks | NVIDIA Developer), the processing performance of “ssd_mobilenet_v2” is 39FPS.
When I tried “ssd_mobilenet_v2”, it was 16FPS-18FPS.
How did you create the benchmark model?

[AastaLLL]

Hi,

May I know how do you benchmark the ssd_mobilenet_v2 performance?
Are you following this instructions?

Deep Learning Inference Benchmarking Instructions

Hi all, below you will find the procedures to run the Jetson Nano deep learning inferencing benchmarks from this blog post with TensorRT. note: for updated JetPack 4.4 benchmarks, please use github.com/NVIDIA-AI-IOT/jetson_benchmarks [image] While using one of the recommended power supplies, make sure you Nano is in 10W performance mode (which is the default mode): $ sudo nvpmodel -m 0 $ sudo jetson_clocks Using other lower-capacity power supplies may lead to system instabilities or shutd…

If not, please give it a try.
Thanks.

[tatsu.ted_2059]

I’m trying the instructions.
Is it possible to use the model (sample_unpruned_mobilenet_v2.uff) provided there to run it in Python code or Deepstream?
I would like to confirm the processing performance when running on Python.

[AastaLLL]

Hi,

It’s recommended to use C++ for benchmark.

But we do have some python-based Deepstream sample here:

GitHub - NVIDIA-AI-IOT/deepstream_python_apps: DeepStream SDK Python bindings...

Thanks.

[tatsu.ted_2059]

Thank you for your answer.
I will try using python-based Deepstream.

After all, is it difficult to get a speed of 39 FPS (30 FPS or more) if it is Python based?