All Projects → NVIDIA-AI-IOT → Jetson_benchmarks

NVIDIA-AI-IOT / Jetson_benchmarks

Licence: mit
Jetson Benchmark

Programming Languages

python
139335 projects - #7 most used programming language

Labels

Projects that are alternatives of or similar to Jetson benchmarks

Volley
Volley is a benchmarking tool for measuring the performance of server networking stacks.
Stars: ✭ 119 (-11.19%)
Mutual labels:  benchmark
Crossplatformdisktest
Windows, macOS and Android storage (HDD, SSD, RAM) speed testing/performance benchmarking app
Stars: ✭ 123 (-8.21%)
Mutual labels:  benchmark
Hpatches Benchmark
Python & Matlab code for local feature descriptor evaluation with the HPatches dataset.
Stars: ✭ 129 (-3.73%)
Mutual labels:  benchmark
Benchmark Driver
Fully-featured benchmark driver for Ruby 3x3
Stars: ✭ 120 (-10.45%)
Mutual labels:  benchmark
Mqperf
Stars: ✭ 122 (-8.96%)
Mutual labels:  benchmark
Meter
Meter - is a simple micro-benchmarking tool for Android (and Java) projects. This is not a profiler, this is very small utility class that designed for making benchmarking easy. Nothing more. Alternative to Android Jetpack Benchmark.
Stars: ✭ 125 (-6.72%)
Mutual labels:  benchmark
Benchmarks
Benchmark of open source, embedded, memory-mapped, key-value stores available from Java (JMH)
Stars: ✭ 116 (-13.43%)
Mutual labels:  benchmark
Vtebench
Generate benchmarks for terminal emulators
Stars: ✭ 131 (-2.24%)
Mutual labels:  benchmark
Benchmark Php
🚀 A benchmark script for PHP and MySQL (Archived)
Stars: ✭ 122 (-8.96%)
Mutual labels:  benchmark
Actors
Evaluation of API and performance of different actor libraries
Stars: ✭ 125 (-6.72%)
Mutual labels:  benchmark
Densematchingbenchmark
Dense Matching Benchmark
Stars: ✭ 120 (-10.45%)
Mutual labels:  benchmark
Babelstream
STREAM, for lots of devices written in many programming models
Stars: ✭ 121 (-9.7%)
Mutual labels:  benchmark
Nas Benchmark
"NAS evaluation is frustratingly hard", ICLR2020
Stars: ✭ 126 (-5.97%)
Mutual labels:  benchmark
Arewefastyet
NOT MAINTAINED ANYMORE! New project is located on https://github.com/mozilla-frontend-infra/js-perf-dashboard -- AreWeFastYet is a set of tools used for benchmarking the major browser's JavaScript virtual machines against each other, as well as reporting the results on a website as insightful graphs showing the evolution of performance over time.
Stars: ✭ 119 (-11.19%)
Mutual labels:  benchmark
Mixbench
A GPU benchmark tool for evaluating GPUs on mixed operational intensity kernels (CUDA, OpenCL, HIP, SYCL)
Stars: ✭ 130 (-2.99%)
Mutual labels:  benchmark
Node Frameworks Benchmark
Simple HTTP benchmark for different nodejs frameworks using wrk
Stars: ✭ 117 (-12.69%)
Mutual labels:  benchmark
Http Router
🎉 Release 2.0 is released! Very fast HTTP router for PHP 7.1+ (incl. PHP8 with attributes) based on PSR-7 and PSR-15 with support for annotations and OpenApi (Swagger)
Stars: ✭ 124 (-7.46%)
Mutual labels:  benchmark
Embedded Ai.bench
benchmark for embededded-ai deep learning inference engines, such as NCNN / TNN / MNN / TensorFlow Lite etc.
Stars: ✭ 131 (-2.24%)
Mutual labels:  benchmark
Gatling Dubbo
A gatling plugin for running load tests on Apache Dubbo(https://github.com/apache/incubator-dubbo) and other java ecosystem.
Stars: ✭ 131 (-2.24%)
Mutual labels:  benchmark
P2plab
performance benchmark infrastructure for IPLD DAGs
Stars: ✭ 126 (-5.97%)
Mutual labels:  benchmark

Benchmarks Targeted for Jetson Xavier NX (Using GPU+2DLA)

The script will run following Benchmarks:

  • Names : Input Image Resolution
  • Inception V4 : 299x299
  • ResNet-50 : 224x224
  • OpenPose : 256x456
  • VGG-19 : 224x224
  • YOLO-V3 : 608x608
  • Super Resolution : 481x321
  • Unet : 256x256

For benchmark results on all NVIDIA Jetson Products; please have a look at NVIDIA jetson_benchmark webpage

Following scripts are included:

  1. Install Requirements for running benchmark script (install_requirements.sh)
  2. CSV files containing parameters (benchmark_csv folder)
  3. Download Model (utils/download_models.py)
  4. Running Benchmark Script (benchmarks.py)

Version Dependencies:

  • JetPack 4.4
  • TensorRT 7

Set up instructions

git clone https://github.com/NVIDIA-AI-IOT/jetson_benchmarks.git
cd jetson_benchmarks
mkdir models # Open folder to store models (Optional)

Install Requirements

sudo sh install_requirements.sh
Note: All libraries will be installed for python3

Download Models

python3 utils/download_models.py --all --csv_file_path <path-to>/benchmark_csv/nx-benchmarks.csv --save_dir <absolute-path-to-downloaded-models>

Running Benchmarks

Running All Benchmark Models at Once

sudo python3 benchmark.py --all --csv_file_path <path-to>/benchmark_csv/nx-benchmarks.csv --model_dir <absolute-path-to-downloaded-models>

Sample Output

Model Name FPS
inception_v4 311.73
vgg19_N2 66.43
super_resolution_bsd500 150.46
unet-segmentation 145.42
pose_estimation 237.1
yolov3-tiny-416 546.69
ResNet50_224x224 824.02
ssd-mobilenet-v1 887.6

Running Individual Benchmark Model

  1. For Inception V4
    sudo python3 benchmark.py --model_name inception_v4 --csv_file_path <path-to>/benchmark_csv/nx-benchmarks.csv --model_dir <absolute-path-to-downloaded-models>

  2. For VGG19
    sudo python3 benchmark.py --model_name vgg19 --csv_file_path <path-to>/benchmark_csv/nx-benchmarks.csv --model_dir <absolute-path-to-downloaded-models>

  3. For Super Resolution
    sudo python3 benchmark.py --model_name super_resolution --csv_file_path <path-to>/benchmark_csv/nx-benchmarks.csv --model_dir <absolute-path-to-downloaded-models>

  4. For UNET Segmentation
    sudo python3 benchmark.py --model_name unet --csv_file_path <path-to>/benchmark_csv/nx-benchmarks.csv --model_dir <absolute-path-to-downloaded-models>

  5. For Pose Estimation
    sudo python3 benchmark.py --model_name pose_estimation --csv_file_path <path-to>/benchmark_csv/nx-benchmarks.csv --model_dir <absolute-path-to-downloaded-models>

  6. For Tiny-YOLO-V3
    sudo python3 benchmark.py --model_name tiny-yolov3 --csv_file_path <path-to>/benchmark_csv/nx-benchmarks.csv --model_dir <absolute-path-to-downloaded-models>

  7. For ResNet-50
    sudo python3 benchmark.py --model_name resnet --csv_file_path <path-to>/benchmark_csv/nx-benchmarks.csv --model_dir <absolute-path-to-downloaded-models>

  8. For SSD-MobileNet-V1 Segmentation
    sudo python3 benchmark.py --model_name ssd-mobilenet-v1 --csv_file_path <path-to>/benchmark_csv/nx-benchmarks.csv --model_dir <absolute-path-to-downloaded-models>

For Jetson AGX Xavier

Please follow setup, and installation requirements.

Download Models

python3 utils/download_models.py --all --csv_file_path <path-to>/benchmark_csv/xavier-benchmarks.csv --save_dir <absolute-path-to-downloaded-models>

Running All Benchmark Models at Once on Jetson AGX Xavier

sudo python3 benchmark.py --all --csv_file_path <path-to>/benchmark_csv/xavier-benchmarks.csv \
                          --model_dir <absolute-path-to-downloaded-models> \
                          --jetson_devkit xavier \
                          --gpu_freq 1377000000 --dla_freq 1395200000 --power_mode 0

For Jetson TX2 and Jeston Nano

Please follow setup, and installation requirements.

Download Models

python3 utils/download_models.py --all --csv_file_path <path-to>/benchmark_csv/tx2-nano-benchmarks.csv --save_dir <absolute-path-to-downloaded-models>

Running All Benchmark Models at Once on Jetson TX2

sudo python3 benchmark.py --all --csv_file_path <path-to>/benchmark_csv/tx2-nano-benchmarks.csv \
                            --model_dir <absolute-path-to-downloaded-models> \
                            --jetson_devkit tx2 \
                            --gpu_freq 1122000000 --power_mode 3 --precision fp16

Running All Benchmark Models at Once on Jetson Nano

sudo python3 benchmark.py --all --csv_file_path <path-to>/benchmark_csv/tx2-nano-benchmarks.csv \
                            --model_dir <absolute-path-to-downloaded-models> \
                            --jetson_devkit nano \
                            --gpu_freq 921600000 --power_mode 0 --precision fp16
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].