Tiny Yolo v3 Frame Rate

[dreihl]

Hi, I’m running Tiny Yolo v3 using: GitHub - pjreddie/darknet: Convolutional Neural Networks , but I’m only getting 3-5 FPS.

According to this document: https://developer.nvidia.com/embedded/jetson-benchmarks , I should be seeing a much higher FPS.

I am running in max power mode.

I would appreciate it if anyone has any thoughts as to why my FPS is so low. Thanks

[AastaLLL]

Hi,

You will need to inference it with TensorRT for optimized performance.
Here are two approaches to do this:

1. Use darknet YOLOv3 with Deepstream

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…

2. Use ONNX YOLOv3 with TensorRT API

GitHub - NVIDIA-AI-IOT/jetson_benchmarks: Jetson Benchmark

Thanks.