How to reproduce the official benmarks of jetson orin nx 16G？

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Description

I want to quickly use the trtexec tool to reproduce the jetson orin nx 16G v3.1 version benmarks data in the link (https://developer.nvidia.com/embedded/jetson-benchmarks). 
The method in the following link does not seem to be what I want (https://github.com/mlcommons/inference_results_v3.1/tree/main/closed/NVIDIA). 
I ​​currently have the following questions: 
1. Where are the corresponding model download links? 
2. What are the corresponding trtexec running parameters?
2

Are you looking for NVIDIA-AI-IOT/jetson_benchmarks: Jetson Benchmark (github.com)?

3

I have read this page and have the following questions:
1. The model in the csv on the page does not seem to correspond to the model on the Jetson Benchmarks | NVIDIA Developer page;
2. I tried to run the program and got the following error：
Please close all other applications and Press Enter to continue…
Setting Jetson orin in max performance mode
Traceback (most recent call last):
File “benchmark.py”, line 130, in
main()
File “benchmark.py”, line 28, in main
system_check.run_set_clocks_withDVFS()
File “/home/jetson/Desktop/benchmark/jetson_benchmarks/utils/utilities.py”, line 47, in run_set_clocks_withDVFS
self.set_clocks_withDVFS(frequency=self.gpu_freq, device=‘gpu’)
File “/home/jetson/Desktop/benchmark/jetson_benchmarks/utils/utilities.py”, line 77, in set_clocks_withDVFS
self.set_frequency(device=device, enable_register=self.enable_register, freq_register=self.freq_register, frequency=frequency, from_freq=from_freq)
File “/home/jetson/Desktop/benchmark/jetson_benchmarks/utils/utilities.py”, line 88, in set_frequency
self.write_internal_register(freq_register1, frequency)
File “/home/jetson/Desktop/benchmark/jetson_benchmarks/utils/utilities.py”, line 108, in write_internal_register
reg_write = open(register, “w”)
FileNotFoundError: [Errno 2] No such file or directory: ‘/sys/kernel/debug/bpmp/debug/clk/nafll_gpc1/rate’

4

I tried commenting out this line of code and got an error:
1、Terminal display
------------Executing ssd_resnet34_1200x1200------------
---------------------- 0 0 0
Error in Build, Please check the log in: ./models
Error in Build, Please check the log in: ./models
Error in Build, Please check the log in: ./models
We recommend to run benchmarking in headless mode

Model Name: ssd_resnet34_1200x1200
FPS:0.00

2、log file display
[07/18/2024-11:16:56] [E] Error opening engine file: ./models/mobilenet_v1_ssd_b32_ws1024_dla1.engine
[07/18/2024-11:16:56] [E] Failed to create engine from model or file.
[07/18/2024-11:16:56] [E] Engine set up failed

5

what’s your problem if you follow the instructions on inference_results_v3.1/closed/NVIDIA at main · mlcommons/inference_results_v3.1 · GitHub?

6

I looked at this page and the process was so complicated that I needed to use trtexec to quickly test and study it.

7

In fact, I just want to use trtexec to reproduce the timing (frame rate) data of the official test @junx2