Jetson TX2上的demo(原创)

Jetson TX2上的demo

一、快速傅里叶-海动图 sample

The CUDA samples directory is copied to the home directory on the device by JetPack. The built binaries are in the following directory:

/home/ubuntu/NVIDIA_CUDA-<version>_Samples/bin/armv7l/linux/release/gnueabihf/

这里的version需要看你自己安装的CUDA版本而定

Run the samples at the command line or by double-clicking on them in the file browser. For example, when you run the oceanFFT sample, the following screen is displayed.

二、车辆识别加框sample

[email protected]:~/tegra_multimedia_api/samples/backend$

./backend 1 ../../data/Video/sample_outdoor_car_1080p_10fps.h264 H264

--trt-deployfile ../../data/Model/GoogleNet_one_class/GoogleNet_modified_oneClass_halfHD.prototxt

--trt-modelfile ../../data/Model/GoogleNet_one_class/GoogleNet_modified_oneClass_halfHD.caffemodel --trt-forcefp32 0 --trt-proc-interval 1 -fps 10

三、GEMM(通用矩阵乘法)测试

[email protected]:/usr/local/cuda/samples/7_CUDALibraries/batchCUBLAS$ ./batchCUBLAS -m1024 -n1024 -k1024

batchCUBLAS Starting...

GPU Device 0: "NVIDIA Tegra X2" with compute capability 6.2

==== Running single kernels ====

Testing sgemm#### args: ta=0 tb=0 m=1024 n=1024 k=1024  alpha = (0xbf800000, -1) beta= (0x40000000, 2)#### args: lda=1024 ldb=1024 ldc=1024

^^^^ elapsed = 0.00372291 sec  [email protected]@@@ sgemm test OK

Testing dgemm#### args: ta=0 tb=0 m=1024 n=1024 k=1024  alpha = (0x0000000000000000, 0) beta= (0x0000000000000000, 0)#### args: lda=1024 ldb=1024 ldc=1024

^^^^ elapsed = 0.10940003 sec  [email protected]@@@ dgemm test OK

==== Running N=10 without streams ====

Testing sgemm#### args: ta=0 tb=0 m=1024 n=1024 k=1024  alpha = (0xbf800000, -1) beta= (0x00000000, 0)#### args: lda=1024 ldb=1024 ldc=1024

^^^^ elapsed = 0.03462315 sec  [email protected]@@@ sgemm test OK

Testing dgemm#### args: ta=0 tb=0 m=1024 n=1024 k=1024  alpha = (0xbff0000000000000, -1) beta= (0x0000000000000000, 0)#### args: lda=1024 ldb=1024 ldc=1024

^^^^ elapsed = 1.09212208 sec  [email protected]@@@ dgemm test OK

==== Running N=10 with streams ====

Testing sgemm#### args: ta=0 tb=0 m=1024 n=1024 k=1024  alpha = (0x40000000, 2) beta= (0x40000000, 2)#### args: lda=1024 ldb=1024 ldc=1024

^^^^ elapsed = 0.03504515 sec  [email protected]@@@ sgemm test OK

Testing dgemm#### args: ta=0 tb=0 m=1024 n=1024 k=1024  alpha = (0xbff0000000000000, -1) beta= (0x0000000000000000, 0)#### args: lda=1024 ldb=1024 ldc=1024

^^^^ elapsed = 1.09177494 sec  [email protected]@@@ dgemm test OK

==== Running N=10 batched ====

Testing sgemm#### args: ta=0 tb=0 m=1024 n=1024 k=1024  alpha = (0x3f800000, 1) beta= (0xbf800000, -1)#### args: lda=1024 ldb=1024 ldc=1024

^^^^ elapsed = 0.03766394 sec  [email protected]@@@ sgemm test OK

Testing dgemm#### args: ta=0 tb=0 m=1024 n=1024 k=1024  alpha = (0xbff0000000000000, -1) beta= (0x4000000000000000, 2)#### args: lda=1024 ldb=1024 ldc=1024

^^^^ elapsed = 1.09389901 sec  [email protected]@@@ dgemm test OK

Test Summary0 error(s)

四、内存带宽测试

[email protected]:/usr/local/cuda/samples/1_Utilities/bandwidthTest$ ./bandwidthTest

[CUDA Bandwidth Test] - Starting...

Running on...

Device 0: NVIDIA Tegra X2

Quick Mode

Host to Device Bandwidth, 1 Device(s)

PINNED Memory Transfers

Transfer Size (Bytes)    Bandwidth(MB/s)

33554432            20215.8

Device to Host Bandwidth, 1 Device(s)

PINNED Memory Transfers

Transfer Size (Bytes)    Bandwidth(MB/s)

33554432            20182.2

Device to Device Bandwidth, 1 Device(s)

PINNED Memory Transfers

Transfer Size (Bytes)    Bandwidth(MB/s)

33554432            35742.8

Result = PASS

NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.

五、设备查询

[email protected]:~/work/TensorRT/tmp/usr/src/tensorrt$ cd /usr/local/cuda/samples/1_Utilities/deviceQuery

[email protected]:/usr/local/cuda/samples/1_Utilities/deviceQuery$ ls

deviceQuery  deviceQuery.cpp  deviceQuery.o  Makefile  NsightEclipse.xml  readme.txt

[email protected]:/usr/local/cuda/samples/1_Utilities/deviceQuery$ ./deviceQuery

./deviceQuery Starting...

CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "NVIDIA Tegra X2"

CUDA Driver Version / Runtime Version          8.0 / 8.0

CUDA Capability Major/Minor version number:    6.2

Total amount of global memory:                 7851 MBytes (8232062976 bytes)

( 2) Multiprocessors, (128) CUDA Cores/MP:     256 CUDA Cores

GPU Max Clock rate:                            1301 MHz (1.30 GHz)

Memory Clock rate:                             1600 Mhz

Memory Bus Width:                              128-bit

L2 Cache Size:                                 524288 bytes

Maximum Texture Dimension Size (x,y,z)         1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)

Maximum Layered 1D Texture Size, (num) layers  1D=(32768), 2048 layers

Maximum Layered 2D Texture Size, (num) layers  2D=(32768, 32768), 2048 layers

Total amount of constant memory:               65536 bytes

Total amount of shared memory per block:       49152 bytes

Total number of registers available per block: 32768

Warp size:                                     32

Maximum number of threads per multiprocessor:  2048

Maximum number of threads per block:           1024

Max dimension size of a thread block (x,y,z): (1024, 1024, 64)

Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 65535)

Maximum memory pitch:                          2147483647 bytes

Texture alignment:                             512 bytes

Concurrent copy and kernel execution:          Yes with 1 copy engine(s)

Run time limit on kernels:                     No

Integrated GPU sharing Host Memory:            Yes

Support host page-locked memory mapping:       Yes

Alignment requirement for Surfaces:            Yes

Device has ECC support:                        Disabled

Device supports Unified Addressing (UVA):      Yes

Device PCI Domain ID / Bus ID / location ID:   0 / 0 / 0

Compute Mode:

< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 8.0, CUDA Runtime Version = 8.0, NumDevs = 1, Device0 = NVIDIA Tegra X2Result = PASS

六、大型项目的测试

详情查看https://developer.nvidia.com/embedded/jetpack

这里面还有一些项目

原文地址:https://www.cnblogs.com/Mufasa/p/8414376.html

时间: 2024-11-02 10:31:55

Jetson TX2上的demo(原创)的相关文章

在Jetson TX2上安装OpenCV(3.4.0)

参考文章:How I built TensorFlow 1.8.0 on Jetson TX2 与参考文章大部分都是相似的,如果不习惯看英文,可以看看我下面的描述 在我们使用python3进行编程时,import cv2不起作用.由于预先安装的opencv是与python2.7绑定的,如果想在python3环境下使用,我们需要重新编译opencv 先决条件 已经在Jetson TX2上安装了JetPack-3.3(或JetPack-3.2.1或JetPack-3.1) 安装步骤 首先清理旧的op

在Jetson TX2上安装caffe和PyCaffe

参考文章:How to Install Caffe and PyCaffe on Jetson TX2 与参考文章大部分都是相似的,如果不习惯看英文,可以看看我下面的描述 caffe是Nvidia TensorRT最支持的深度学习框架,因此在Jetson TX2上安装caffe很有必要.顺便说一句,下面的安装是支持python3的. 先决条件 在Jetson TX2上完成JetPack-3.1的安装. 构建并安装OpenCV-3.4.0,并确保其在python3下正常工作.参考:在Jetson

Jetson TX2火力全开

Jetson Tegra系统的应用涵盖越来越广,相应用户对性能和功耗的要求也呈现多样化.为此NVIDIA提供一种新的命令行工具,可以方便地让用户配置CPU状态,以最大限度地提高不同场景下的性能和能耗. 记住,Jetson TX2由一个GPU和一个CPU集群组成. CPU集群由双核丹佛2处理器和四核ARM Cortex-A57组成,通过高性能互连架构连接. 拥有6个CPU核心和一个GPU,您可以不必自行运行所有性能/功耗来测试最佳的运行状态,因为NVIDIA的新的命令工具Nvpmodel,提供了5

NVIDIA Jetson TX2 on GreenGrass

如果您刚开始使用 AWS IoT Greengrass,我们建议您使用 Raspberry Pi 或 Amazon EC2 实例作为您的核心设备,并且按照适合您的设备的设置步骤进行操作.要使用不同的设备或平台,请按照本部分中的步骤操作.有关支持的设备平台的信息,请参阅 Greengrass 核心平台兼容性. 如果您的核心设备是 NVIDIA Jetson TX2,您必须先使用 JetPack 3.3 安装程序切换该固件.如果要配置不同的设备,请跳至步骤 2. 注意 您使用的 JetPack 安装

Jetson TX2刷机教程(原创)

Jetson TX2刷机教程 一,硬件准备 1台host主机(linux系统,最好是ubuntu64位) 1台Jetson TX2的平台 二,软件包 JetPack(Jetson SDK) 下载地址:https://developer.nvidia.com/embedded/downloads#?search=jetpack%203.1 三,安装过程 1.在host主机中下载的JetPack(Jetson SDK)软件包 2.将下载的软件包右键,选择properties,勾选Allow exec

Jetson TX2安装Jetpack 3.0注意事项

Jetson TX2安装Jetpack 3.0注意事项 nvidia jetson tx2配置caffe: http://blog.csdn.net/jiongnima/article/details/70040262 CSDN jiongnima博主的这篇文章非常详细完整,但是作为一个初次接触nvidia jetson TX2的人来说,还是会难免遇到一些困难,下面我在这篇文章的基础上,写一些我在安转Jetpack 3.0时遇到的问题,希望大家可以坐在以后的安装过程中规避这些问题:  1.在nv

Jetson TX2安装TensorFlow注意事项

Jetson TX2安装TensorFlow注意事项 在nvidia jetson TX 2上安装TensorFlow时,在使用下面教程进行安装时,可能会出现多次卡死在编译阶段:./buildTensorFlow.sh: nvidia jetson tx2 安装TensorFlow:http://www.ncnynl.com/archives/201706/1754.html 解决方法:引发该错误的原因是内存不足,可以通过通过Ubuntu中的swap分区分配2G虚拟内存,来解决内存不足的问题:

Jetson TX2安装tensorflow

Jetson TX2安装tensorflow 大致分为两步: 一.划分虚拟内存 原因:Jetson TX2自带8G内存这个内存空间在安装tensorflow编译过程中会出现内存溢出引发的安装进程奔溃 1. 创建8G大小的swapfile fallocate -l 8G swapfile 2. 更改swapfile的权限 chmod 600 swapfile 3. 创建swap区 mkswap swapfile 4. 激活swap区 sudo swapon swapfile 5. 确认swap区在

往github上传demo

一直在github上寻找demo,但怎么传demo上githun呢? http://www.2cto.com/kf/201504/390397.html 首先在github上 new一个repository工程: 两种方法,一种是在xcode里面选择git,填上git地址,进行commit & push 还有一种是通过命令行进入你的ios项目文件夹,然后执行 git init git remote add origin you_project_url_on_git git add . git c