Comparison of Benchmark Test Performance on NVIDIA AGX Xavier, Xavier NX and Nano

Comparison of Benchmark Test Performance on NVIDIA AGX Xavier, Xavier NX and Nano

Jetson AGX Xavier | Jetson Nano | Jetson Xavier NX

17 March 2021
WHAT YOU WILL LEARN?

1- Cloning the test repository

2- Setting up the benchmark test

3- Testing the performance in each device




ENVIRONMENT

Hardware 1: Jetson AGX Xavier Developer Kit

Hardware 2: DSBOX-NX2

Hardware 3: DSBOX-N2

OS 1: JetPack 4.4 (L4T-32.4.3)

OS 2: JetPack 4.5 (L4T-32.5)

OS 3: JetPack 4.5 (L4T-32.5)

Performance Test Setup


First, let's set our test environment from github:


git clone https://github.com/NVIDIA-AI-IOT/jetson_benchmarks.git
cd jetson_benchmarks
mkdir models
sudo sh install_requirements.sh


Now let's download all model files:


For AGX Xavier:


python3 utils/download_models.py --all --csv_file_path ${PWD}/benchmark_csv/xavier-benchmarks.csv --save_dir ${PWD}/models


For Xavier NX:


python3 utils/download_models.py --all --csv_file_path ${PWD}/benchmark_csv/nx-benchmarks.csv --save_dir ${PWD}/models


For Nano:


python3 utils/download_models.py --all --csv_file_path ${PWD}/benchmark_csv/tx2-nano-benchmarks.csv --save_dir ${PWD}/models

Jetson AGX Xavier Test Results


Let's test all models one by one:


sudo python3 benchmark.py --model_name inception_v4 --csv_file_path ${PWD}/benchmark_csv/xavier-benchmarks.csv --model_dir ${PWD}/models --jetson_devkit xavier --gpu_freq 1377000000 --dla_freq 1395200000 --power_mode 0



sudo python3 benchmark.py --model_name vgg19 --csv_file_path ${PWD}/benchmark_csv/xavier-benchmarks.csv --model_dir ${PWD}/models --jetson_devkit xavier --gpu_freq 1377000000 --dla_freq 1395200000 --power_mode 0



sudo python3 benchmark.py --model_name super_resolution --csv_file_path ${PWD}/benchmark_csv/xavier-benchmarks.csv --model_dir ${PWD}/models --jetson_devkit xavier --gpu_freq 1377000000 --dla_freq 1395200000 --power_mode 0



sudo python3 benchmark.py --model_name unet --csv_file_path ${PWD}/benchmark_csv/xavier-benchmarks.csv --model_dir ${PWD}/models --jetson_devkit xavier --gpu_freq 1377000000 --dla_freq 1395200000 --power_mode 0



sudo python3 benchmark.py --model_name pose_estimation --csv_file_path ${PWD}/benchmark_csv/xavier-benchmarks.csv --model_dir ${PWD}/models --jetson_devkit xavier --gpu_freq 1377000000 --dla_freq 1395200000 --power_mode 0



sudo python3 benchmark.py --model_name tiny-yolov3 --csv_file_path ${PWD}/benchmark_csv/xavier-benchmarks.csv --model_dir ${PWD}/models --jetson_devkit xavier --gpu_freq 1377000000 --dla_freq 1395200000 --power_mode 0



cansend can0 123#1122334455667788



sudo python3 benchmark.py --model_name ssd-mobilenet-v1 --csv_file_path ${PWD}/benchmark_csv/xavier-benchmarks.csv --model_dir ${PWD}/models --jetson_devkit xavier --gpu_freq 1377000000 --dla_freq 1395200000 --power_mode 0


Jetson Xavier NX Test Results


Let's test all models one by one:


sudo python3 benchmark.py --model_name inception_v4 --csv_file_path ${PWD}/benchmark_csv/nx-benchmarks.csv --model_dir ${PWD}/models/ --power_mode



sudo python3 benchmark.py --model_name vgg19 --csv_file_path ${PWD}/benchmark_csv/nx-benchmarks.csv --model_dir ${PWD}/models/ --power_mode 2



sudo python3 benchmark.py --model_name super_resolution --csv_file_path ${PWD}/benchmark_csv/nx-benchmarks.csv --model_dir ${PWD}/models/ --power_mode 2



sudo python3 benchmark.py --model_name unet --csv_file_path ${PWD}/benchmark_csv/nx-benchmarks.csv --model_dir ${PWD}/models/ --power_mode 2



sudo python3 benchmark.py --model_name pose_estimation --csv_file_path ${PWD}/benchmark_csv/nx-benchmarks.csv --model_dir ${PWD}/models/ --power_mode 2



sudo python3 benchmark.py --model_name tiny-yolov3 --csv_file_path ${PWD}/benchmark_csv/nx-benchmarks.csv --model_dir ${PWD}/models/ --power_mode 2



sudo python3 benchmark.py --model_name resnet --csv_file_path ${PWD}/benchmark_csv/nx-benchmarks.csv --model_dir ${PWD}/models/ --power_mode 2



sudo python3 benchmark.py --model_name ssd-mobilenet-v1 --csv_file_path ${PWD}/benchmark_csv/nx-benchmarks.csv --model_dir ${PWD}/models/ --power_mode 2

Jetson Nano Test Results


Let's test all models one by one (with fp16 model):


sudo python3 benchmark.py --model_name inception_v4 --csv_file_path ${PWD}/benchmark_csv/tx2-nano-benchmarks.csv --model_dir ${PWD}/models/ --jetson_devkit nano --gpu_freq 921600000 --power_mode 0 --precision fp16



sudo python3 benchmark.py --model_name vgg19 --csv_file_path ${PWD}/benchmark_csv/tx2-nano-benchmarks.csv --model_dir ${PWD}/models/ --jetson_devkit nano --gpu_freq 921600000 --power_mode 0 --precision fp16



sudo python3 benchmark.py --model_name super_resolution --csv_file_path ${PWD}/benchmark_csv/tx2-nano-benchmarks.csv --model_dir ${PWD}/models/ --jetson_devkit nano --gpu_freq 921600000 --power_mode 0 --precision fp16



sudo python3 benchmark.py --model_name unet --csv_file_path ${PWD}/benchmark_csv/tx2-nano-benchmarks.csv --model_dir ${PWD}/models/ --jetson_devkit nano --gpu_freq 921600000 --power_mode 0 --precision fp16



sudo python3 benchmark.py --model_name pose_estimation --csv_file_path ${PWD}/benchmark_csv/tx2-nano-benchmarks.csv --model_dir ${PWD}/models/ --jetson_devkit nano --gpu_freq 921600000 --power_mode 0 --precision fp16



sudo python3 benchmark.py --model_name tiny-yolov3 --csv_file_path ${PWD}/benchmark_csv/tx2-nano-benchmarks.csv --model_dir ${PWD}/models/ --jetson_devkit nano --gpu_freq 921600000 --power_mode 0 --precision fp16



sudo python3 benchmark.py --model_name tiny-yolov3 --csv_file_path ${PWD}/benchmark_csv/tx2-nano-benchmarks.csv --model_dir ${PWD}/models/ --jetson_devkit nano --gpu_freq 921600000 --power_mode 0 --precision fp16



sudo python3 benchmark.py --model_name ssd-mobilenet-v1 --csv_file_path ${PWD}/benchmark_csv/tx2-nano-benchmarks.csv --model_dir ${PWD}/models/ --jetson_devkit nano --gpu_freq 921600000 --power_mode 0 --precision fp16


Comparison of Results


Thank you for reading our blog post. 


If you want to get updated on new blog posts, product launches and discounts, you can fill out the form and sign up for our newsletter. By signing up, you can reach various blog posts about AI, deep learning, machine vision, high-speed cameras, and industrial interfaces. 


You will receive a "free shipping" code for next purchase immediately.

English