Nvidia在边缘计算/Xavier推出的最低配版GPU运算平台
Jetson Nano 开发者套件入门
https://developer.nvidia.com/zh-cn/embedded/learn/get-started-jetson-nano-devkit
官方培训课程(需注册)
https://courses.nvidia.com/courses/course-v1:DLI+S-RX-02+V2/info
包含一个板载内存和处理器核心(带大大的散热器),和一块承载的板
GPU | NVIDIA Maxwell architecture with 128 NVIDIA CUDA® cores |
---|---|
CPU | Quad-core ARM Cortex-A57 MPCore processor |
Memory | 4 GB 64-bit LPDDR4, 1600MHz 25.6 GB/s |
Storage | 16 GB eMMC 5.1 |
Video Encode | 250MP/sec 1x 4K @ 30 (HEVC) 2x 1080p @ 60 (HEVC) 4x 1080p @ 30 (HEVC) 4x 720p @ 60 (HEVC) 9x 720p @ 30 (HEVC) |
Video Decode | 500MP/sec 1x 4K @ 60 (HEVC) 2x 4K @ 30 (HEVC) 4x 1080p @ 60 (HEVC) 8x 1080p @ 30 (HEVC) 9x 720p @ 60 (HEVC) |
Camera | 12 lanes (3x4 or 4x2) MIPI CSI-2 D-PHY 1.1 (1.5 Gb/s per pair) |
Connectivity | Gigabit Ethernet, M.2 Key E |
Display | HDMI 2.0 and eDP 1.4 |
USB | 4x USB 3.0, USB 2.0 Micro-B |
Others | GPIO, I2C, I2S, SPI, UART |
Mechanical | 69.6 mm x 45 mm 260-pin edge connector |
https://developer.nvidia.com/embedded/jetson-nano
Developer kit carrier boards 两个版本,分别支持4GB和2GB内存
1. 硬件准备 - 买买买,注意电源输入,5V3A配合跳线设置,电压太高烧了,电流太低性能不能出来
2. 安装操作系统 - https://developer.nvidia.com/jetson-nano-sd-card-image 用Rufus之类的工具烧录启动盘一样操作就行
3. 升级环境 - 和ubuntu的操作基本一致
# 扩容操作 2GB -> 4GB # 参考DLI教程
free -m
sudo systemctl disable nvzramconfig
sudo falcate -l 4G /mnt/4GB.swap
sudo chmod 600 /mnt/4GB.swap
sudo mkswap /mnt/4GB.swap
sudo vi /etc /fstab
# /mnt/4GB.swap swap swap defaults 0 0
sudo reboot
free -m
# Docker安装 # 参考DLI教程
mkdir -p ~/nvdli-data
sudo docker run --runtime nvidia -it --rm --network host \
--volume ~/nvdli-data:/nvdli-nano/data \
--device /dev/video0 \
nvcr.io/nvidia/dli/dli-nano-ai:<tag>
echo "sudo docker run --runtime nvidia -it --rm --network host \
--volume ~/nvdli-data:/nvdli-nano/data \
--device /dev/video0 \
nvcr.io/nvidia/dli/dli-nano-ai:v2.0.1-r32.4.4" > docker_dli_run.sh
chmod +x docker_dli_run.sh
./docker_dli_run.sh
# http://192.168.55.1:8888/ # dlinano
# Python3环境
sudo apt update
sudo apt list full-upgrade
sudo apt install python3
sudo apt install python3-pip
# which python3
ln -s /usr/bin/python3 /usr/bin/python
# pip3 -> pip
pip install --upgrade pip
pip install virtualenv
# Headless 支持远程登陆
sudo apt install net-tools
sudo apt install ssh
sudo apt-get update
sudo apt-get install libhdf5-serial-dev hdf5-tools libhdf5-dev \
zlib1g-dev zip libjpeg8-dev liblapack-dev libblas-dev gfortran
sudo apt-get install python3-pip
sudo pip3 install -U pip testresources setuptools==49.6.0
sudo pip3 install -U numpy==1.19.4 future==0.18.2 mock==3.0.5 \
h5py==2.10.0 keras_preprocessing==1.1.1 \
keras_applications==1.0.8 gast==0.2.2 futures protobuf pybind11
sudo pip3 install --extra-index-url \
https://developer.download.nvidia.com/compute/redist/jp/v$JP_VERSION tensorflow
sudo apt-get install virtualenv
python3 -m virtualenv -p python3 <chosen_venv_name>
# CUDA
sudo gedit ~/.bashrc
export CUBA_HOME=/usr/local/cuda-10.2
export LD_LIBRARY_PATH=/usr/local/cuda-10.2/lib64:$LD_LIBRARY_PATH
export PATH=/usr/local/cuda-10.2/bin:$PATH
source ~/.bashrc
# Jetson Nano 开发者套件入门
https://developer.nvidia.com/embedded/learn/get-started-jetson-nano-devkit
# TensorFlow Installation for Jetson Platform
https://docs.nvidia.com/deeplearning/frameworks/install-tf-jetson-platform/index.html
# Camera
https://cloud.tencent.com/developer/article/1421907
# Getting Started
https://developer.nvidia.com/embedded/learn/getting-started-jetson#tutorials
# Run Tensorflow models on the Jetson Nano with TensorRT
https://gilberttanner.com/blog/run-tensorflow-on-the-jetson-nano
原创声明:本文系作者授权腾讯云开发者社区发表,未经许可,不得转载。
如有侵权,请联系 cloudcommunity@tencent.com 删除。
原创声明:本文系作者授权腾讯云开发者社区发表,未经许可,不得转载。
如有侵权,请联系 cloudcommunity@tencent.com 删除。