< >
Home » NX入门教程软件篇 » NX入门教程软件篇-安装openpose(jetpack4.4)

NX入门教程软件篇-安装openpose(jetpack4.4)

NX入门教程软件篇-安装openpose(jetpack4.4)

说明：

  • 介绍如何安装openpose
  • 基于官方的脚本做修改

步骤：

mkdir -p ~/dl/openpose
cd ~/dl/openpose
git clone https://github.com/CMU-Perceptual-Computing-Lab/openpose
cd openpose
rm -rf ./3rdparty/caffe && mkdir ./3rdparty/caffe
git submodule update --init --recursive --remote
  • 安装caffe，上面的方式已经下载了caffe，位于~/dl/openpose/openpose/3rdparty
  • 增加安装脚本和配置文件
cd ~/dl/openpose/openpose/3rdparty/caffe
  • 新建vim install_caffe_JetsonNX_JetPack4.4.sh
  • 内容如下：
#!/bin/bash
echo "------------------------- Installing Caffe -------------------------"
echo "NOTE: This script assumes that just flashed JetPack 4.4 : Ubuntu 18, CUDA 10.2, cuDNN 8 and OpenCV are already installed on your machine. Otherwise, it might fail."

function exitIfError {
    if [[ $? -ne 0 ]] ; then
        echo ""
        echo "------------------------- -------------------------"
        echo "Errors detected. Exiting script. The software might have not been successfully installed."
        echo "------------------------- -------------------------"
        exit 1
    fi
}

echo "------------------------- Checking Ubuntu Version -------------------------"
# If you respected the installation assumptions, nothing to do. 
echo "------------------------- Ubuntu Version Checked -------------------------"
echo ""
echo "------------------------- Installing some Caffe Dependencies -------------------------"
# Basic
sudo apt-get --assume-yes update
sudo apt-get --assume-yes install build-essential
# General dependencies
sudo apt-get --assume-yes install libprotobuf-dev libleveldb-dev libsnappy-dev libhdf5-serial-dev protobuf-compiler libatlas-base-dev
sudo apt-get --assume-yes install --no-install-recommends libboost-all-dev
sudo apt-get --assume-yes install libgflags-dev libgoogle-glog-dev liblmdb-dev
# Python libs
sudo apt-get --assume-yes install python-pip python-dev build-essential
sudo -H pip install --upgrade pip
sudo -H pip install --upgrade numpy protobuf
# OpenCV is provided for tegra in JetPack
exitIfError
echo "------------------------- Some Caffe Dependencies Installed -------------------------"
echo ""
echo "------------------------- Compiling Caffe -------------------------"
sudo sed -i -e 's/cudnn.h/cudnn_version.h/g' cmake/Cuda.cmake
cp Makefile.config.Ubuntu18_cuda10_JetsonNX_JetPack44 Makefile.config
make all -j`nproc` && make distribute -j`nproc`
# make test -j`nproc`
# make runtest -j`nproc`
exitIfError
echo "------------------------- Caffe Compiled -------------------------"
echo ""
echo "------------------------- Caffe Installed -------------------------"
echo ""
  • 新建vim Makefile.config.Ubuntu18_cuda10_JetsonNX_JetPack44
  • 内容如下：
## Refer to http://caffe.berkeleyvision.org/installation.html
# Contributions simplifying and improving our build system are welcome!

# cuDNN acceleration switch (uncomment to build with cuDNN).
USE_CUDNN := 1

# CPU-only switch (uncomment to build without GPU support).
# CPU_ONLY := 1

# uncomment to disable IO dependencies and corresponding data layers
# USE_OPENCV := 0
# USE_LEVELDB := 0
# USE_LMDB := 0

# uncomment to allow MDB_NOLOCK when reading LMDB files (only if necessary)
#   You should not set this flag if you will be reading LMDBs with any
#   possibility of simultaneous read and write
# ALLOW_LMDB_NOLOCK := 1

#Uncomment and set accordingly if you're using OpenCV 3/4
OPENCV_VERSION := 4

# To customize your choice of compiler, uncomment and set the following.
# N.B. the default for Linux is g++ and the default for OSX is clang++
# CUSTOM_CXX := g++

# CUDA directory contains bin/ and lib/ directories that we need.
CUDA_DIR := /usr/local/cuda
# On Ubuntu 14.04, if cuda tools are installed via
# "sudo apt-get install nvidia-cuda-toolkit" then use this instead:
# CUDA_DIR := /usr

# CUDA architecture setting: going with all of them.
# For CUDA < 6.0, comment the *_50 through *_61 lines for compatibility.
# For CUDA < 8.0, comment the *_60 and *_61 lines for compatibility.
CUDA_ARCH := -gencode arch=compute_30,code=sm_30 \
        -gencode arch=compute_35,code=sm_35 \
        -gencode arch=compute_50,code=sm_50 \
        -gencode arch=compute_52,code=sm_52 \
        -gencode arch=compute_60,code=sm_60 \
        -gencode arch=compute_61,code=sm_61 \
        -gencode arch=compute_61,code=compute_61 \
        -gencode arch=compute_72,code=compute_72

# BLAS choice:
# atlas for ATLAS (default)
# mkl for MKL
# open for OpenBlas
BLAS := atlas
# Custom (MKL/ATLAS/OpenBLAS) include and lib directories.
# Leave commented to accept the defaults for your choice of BLAS
# (which should work)!
# BLAS_INCLUDE := /path/to/your/blas
# BLAS_LIB := /path/to/your/blas

# Homebrew puts openblas in a directory that is not on the standard search path
# BLAS_INCLUDE := $(shell brew --prefix openblas)/include
# BLAS_LIB := $(shell brew --prefix openblas)/lib

# This is required only if you will compile the matlab interface.
# MATLAB directory should contain the mex binary in /bin.
# MATLAB_DIR := /usr/local
# MATLAB_DIR := /Applications/MATLAB_R2012b.app

# NOTE: this is required only if you will compile the python interface.
# We need to be able to find Python.h and numpy/arrayobject.h.
PYTHON_INCLUDE := /usr/include/python2.7 \
        /usr/lib/python2.7/dist-packages/numpy/core/include \
        /usr/local/lib/python2.7/dist-packages/numpy/core/include
# Anaconda Python distribution is quite popular. Include path:
# Verify anaconda location, sometimes it's in root.
# ANACONDA_HOME := $(HOME)/anaconda
# PYTHON_INCLUDE := $(ANACONDA_HOME)/include \
        # $(ANACONDA_HOME)/include/python2.7 \
        # $(ANACONDA_HOME)/lib/python2.7/site-packages/numpy/core/include

# Uncomment to use Python 3 (default is Python 2)
# PYTHON_LIBRARIES := boost_python3 python3.5m
# PYTHON_INCLUDE := /usr/include/python3.5m \
#                 /usr/lib/python3.5/dist-packages/numpy/core/include

# We need to be able to find libpythonX.X.so or .dylib.
PYTHON_LIB := /usr/lib /usr/local/lib
# PYTHON_LIB := $(ANACONDA_HOME)/lib

# Homebrew installs numpy in a non standard path (keg only)
# PYTHON_INCLUDE += $(dir $(shell python -c 'import numpy.core; print(numpy.core.__file__)'))/include
# PYTHON_LIB += $(shell brew --prefix numpy)/lib

# Uncomment to support layers written in Python (will link against Python libs)
# WITH_PYTHON_LAYER := 1

# Whatever else you find you need goes here.
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial
LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib /usr/lib/aarch64-linux-gnu /usr/lib/aarch64-linux-gnu/hdf5/serial

# If Homebrew is installed at a non standard location (for example your home directory) and you use it for general dependencies
# INCLUDE_DIRS += $(shell brew --prefix)/include
# LIBRARY_DIRS += $(shell brew --prefix)/lib

# NCCL acceleration switch (uncomment to build with NCCL)
# https://github.com/NVIDIA/nccl (last tested version: v1.2.3-1+cuda8.0)
# USE_NCCL := 1

# Uncomment to use `pkg-config` to specify OpenCV library paths.
# (Usually not necessary -- OpenCV libraries are normally installed in one of the above $LIBRARY_DIRS.)
# USE_PKG_CONFIG := 1

# N.B. both build and distribute dirs are cleared on `make clean`
BUILD_DIR := build
DISTRIBUTE_DIR := distribute

# Uncomment for debugging. Does not work on OSX due to https://github.com/BVLC/caffe/issues/171
# DEBUG := 1

# The ID of the GPU that 'make runtest' will use to run unit tests.
TEST_GPUID := 0

# enable pretty build (comment to see full commands)
Q ?= @
  • 在NX下容易出现找不到opencv2，增加如下行：
sudo ln -s /usr/include/opencv4/opencv2 /usr/include/

ifeq ($(OPENCV_VERSION), $(filter $(OPENCV_VERSION), 3 4))
    LIBRARIES += opencv_imgcodecs
endif
ifeq ($(OPENCV_VERSION), 4)
    ifeq ($(USE_PKG_CONFIG), 1)
        INCLUDE_DIRS += $(shell pkg-config opencv4 --cflags-only-I | sed 's/-I//g')
    else
        INCLUDE_DIRS += /usr/include/opencv4 /usr/local/include/opencv4
        INCLUDE_DIRS += /usr/include/opencv4/opencv /usr/local/include/opencv4/opencv
    endif
endif
........
ifeq ($(USE_PKG_CONFIG), 1)
    ifeq ($(OPENCV_VERSION), 4)
        PKG_CONFIG := $(shell pkg-config opencv4 --libs)
    else
        PKG_CONFIG := $(shell pkg-config opencv --libs)
    endif
else
  • Makefile.config.example文件
# Uncomment and set accordingly if you're using OpenCV 3/4
# OPENCV_VERSION := 3
  • src/caffe/layers/window_data_layer.cpp文件
  cv_img = cv::imread(image.first, cv::IMREAD_COLOR);
if (!cv_img.data) {
  LOG(ERROR) << "Could not open or find file " << image.first;
  return;
  • src/caffe/test/test_io.cpp文件
  int cv_read_flag = (is_color ? cv::IMREAD_COLOR :
    cv::IMREAD_GRAYSCALE);
  • src/caffe/util/io.cpp 文件
  cv::Mat cv_img;
  int cv_read_flag = (is_color ? cv::IMREAD_COLOR :
    cv::IMREAD_GRAYSCALE);
  cv::Mat cv_img_origin = cv::imread(filename, cv_read_flag);
   ..........
  std::vector<char> vec_data(data.c_str(), data.c_str() + data.size());
  int cv_read_flag = (is_color ? cv::IMREAD_COLOR :
    cv::IMREAD_GRAYSCALE);
  cv_img = cv::imdecode(vec_data, cv_read_flag);
  • 执行安装
sudo chmod +x  install_caffe_JetsonNX_JetPack4.4.sh
./install_caffe_JetsonNX_JetPack4.4.sh
  • 再安装openpose并下载模型
cd ~/dl/openpose/openpose/scripts/ubuntu/
  • 新建文件vim install_openpose_JetsonNX_JetPack4.4.sh
  • 内容如下：
#!/bin/bash



echo "------------------------- Installing OpenPose -------------------------"
echo "NOTE: This script assumes that just flashed JetPack 4.4 : Ubuntu 18, CUDA 10.2, cuDNN 8 and OpenCV are already installed on your machine. Otherwise, it might fail."

function exitIfError {
    if [[ $? -ne 0 ]] ; then
        echo ""
        echo "------------------------- -------------------------"
        echo "Errors detected. Exiting script. The software might have not been successfully installed."
        echo "------------------------- -------------------------"
        exit 1
    fi
}



function executeShInItsFolder {
    # $1 = sh file name
    # $2 = folder where the sh file is
    # $3 = folder to go back
    cd $2
    exitIfError
    sudo chmod +x $1
    exitIfError
    bash ./$1
    exitIfError
    cd $3
    exitIfError
}



echo "------------------------- Compiling OpenPose -------------------------"
# Copy Makefile & Makefile.config
sed -i -e 's/cudnn.h/cudnn_version.h/g' cmake/Cuda.cmake
sed -i -e 's/cudnn.h/cudnn_version.h/g' cmake/Modules/FindCuDNN.cmake
#cp scripts/ubuntu/Makefile.example Makefile
#cp scripts/ubuntu/Makefile.config.Ubuntu18_cuda10_JetsonNX_JetPack44 Makefile.config
cmake .
# Compile OpenPose
make all -j`nproc`
exitIfError
echo "------------------------- OpenPose Compiled -------------------------"
echo ""



echo "------------------------- Downloading OpenPose Models -------------------------"
executeShInItsFolder "getModels.sh" "./models" ".."
exitIfError
echo "Models downloaded"
echo "------------------------- OpenPose Models Downloaded -------------------------"
echo ""



echo "------------------------- OpenPose Installed -------------------------"
echo ""
  • 新建文件vim Makefile.config.Ubuntu18_cuda10_JetsonNX_JetPack44
  • 内容如下：
## Refer to http://caffe.berkeleyvision.org/installation.html
# Contributions simplifying and improving our build system are welcome!

# CPU-only switch (comment to build without GPU support).
USE_CUDA := 1

# uncomment to disable IO dependencies and corresponding data layers
# USE_OPENCV := 0
# USE_LEVELDB := 0
# USE_LMDB := 0

# uncomment to allow MDB_NOLOCK when reading LMDB files (only if necessary)
#   You should not set this flag if you will be reading LMDBs with any
#   possibility of simultaneous read and write
# ALLOW_LMDB_NOLOCK := 1

# Uncomment if you're using OpenCV 3
OPENCV_VERSION := 4

# To customize your choice of compiler, uncomment and set the following.
# N.B. the default for Linux is g++ and the default for OSX is clang++
# CUSTOM_CXX := g++

# CUDA directory contains bin/ and lib/ directories that we need.
CUDA_DIR := /usr/local/cuda
# On Ubuntu 14.04, if cuda tools are installed via
# "sudo apt-get install nvidia-cuda-toolkit" then use this instead:
# CUDA_DIR := /usr

# CUDA architecture setting: going with all of them.
# For CUDA < 6.0, comment the *_50 through *_61 lines for compatibility.
# For CUDA < 8.0, comment the *_60 and *_61 lines for compatibility.
CUDA_ARCH := -gencode arch=compute_30,code=sm_30 \
        -gencode arch=compute_35,code=sm_35 \
        -gencode arch=compute_50,code=sm_50 \
        -gencode arch=compute_52,code=sm_52 \
        -gencode arch=compute_60,code=sm_60 \
        -gencode arch=compute_61,code=sm_61 \
        -gencode arch=compute_61,code=compute_61 \
        -gencode arch=compute_72,code=compute_72



# Uncomment to enable op::Profiler
# PROFILER_ENABLED := 1

# DEEP_NET choice:
# caffe for Caffe (default and only option so far)
DEEP_NET := caffe

# Caffe directory
CAFFE_DIR := 3rdparty/caffe/distribute

# Faster GUI display
# WITH_OPENCV_WITH_OPENGL := 1
# OpenPose 3-D Reconstruction
# WITH_3D_RENDERER := 1
# WITH_CERES := 1
# WITH_FLIR_CAMERA := 1
# Eigen directory (Ceres)
# WITH_EIGEN := 1
EIGEN_DIR := /usr/include/eigen3/
# Spinnaker directory
SPINNAKER_DIR := /usr/include/spinnaker

# Whatever else you find you need goes here.
INCLUDE_DIRS := /usr/local/include /usr/include/hdf5/serial
LIBRARY_DIRS := /usr/local/lib /usr/lib /usr/lib/aarch64-linux-gnu /usr/lib/aarch64-linux-gnu/hdf5/serial

# If Homebrew is installed at a non standard location (for example your home directory) and you use it for general dependencies
# INCLUDE_DIRS += $(shell brew --prefix)/include
# LIBRARY_DIRS += $(shell brew --prefix)/lib

# Uncomment to use `pkg-config` to specify OpenCV library paths.
# (Usually not necessary -- OpenCV libraries are normally installed in one of the above $LIBRARY_DIRS.)
# USE_PKG_CONFIG := 1

BUILD_DIR := build
DISTRIBUTE_DIR := distribute

# Uncomment for debugging. Does not work on OSX due to https://github.com/BVLC/caffe/issues/171
# DEBUG := 1

# The ID of the GPU that 'make runtest' will use to run unit tests.
TEST_GPUID := 0

# enable pretty build (comment to see full commands)
Q ?= @
  • 编译Openpose、下载Caffe models
cd ~/dl/openpose/openpose/
sudo chmod +x scripts/ubuntu/install_openpose_JetsonNX_JetPack4.4.sh
bash ./scripts/ubuntu/install_openpose_JetsonNX_JetPack4.4.sh
  • 运行完成后会在./build_release 目录中生成相关运行文件
./build/examples/openpose/openpose.bin

测试：

  • 加载环境
export LC_ALL=en_US.UTF-8
export LD_LIBRARY_PATH=~/dl/openpose/openpose/3rdparty/caffe/build/lib/:$LD_LIBRARY_PATH
  • 如果之前没有下载好模型，可以单独下载
cd ~/dl/openpose/openpose/models
./getModels.sh
  • 运行openpose，测试视频
./examples/openpose/openpose.bin --video ./examples/media/video.avi --model_folder ./models/
  • 运行openpose，相机测试
  • 先接usb摄像头，确保相机能正常使用
./examples/openpose/openpose.bin -camera_resolution 640x480 -net_resolution 128x96

参考：

  • https://spyjetson.blogspot.com/2020/07/jetson-xavier-nx-human-pose-estimation.html

纠错,疑问,交流: 请进入讨论区或 点击加入Q群

获取最新文章: 扫一扫右上角的二维码加入“创客智造”公众号


标签: nx入门教程软件篇