编译安装飞桨fastdeploy@FreeBSD（失败）

2024-03-26 11:12
文章标签 编译 安装 失败 飞桨 freebsd fastdeploy

本文主要是介绍编译安装飞桨fastdeploy@FreeBSD（失败），希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

FastDeploy是一款全场景、易用灵活、极致高效的AI推理部署工具， 支持云边端部署。提供超过 🔥160+ Text，Vision， Speech和跨模态模型📦开箱即用的部署体验，并实现🔚端到端的推理性能优化。包括 物体检测、字符识别（OCR）、人脸、人像扣图、多目标跟踪系统、NLP、Stable Diffusion文图生成、TTS 等几十种任务场景，满足开发者多场景、多硬件、多平台的产业部署需求。官网：GitHub - PaddlePaddle/FastDeploy: ⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization, multi-platform and multi-framework support.

遗憾的是在FreeBSD下没有装成。

发现fastdeploy需要opencv-python，所以花了很大的精力来安装，但是也没有装上。opencv可以用Pillow代替，但是后面还是碰到没法解决的问题。

编译安装opencv-python

编译安装没完成，估计还是用pkg install opencv-python装成的。

需要安装opencv-pyhton

安装opencv-python

pip install opencv-python，但是装不上，所以选择源代码编译安装

先安装pip install scikit-build

然后下载opencv-python源代码

可以用git clone https://github.com/opencv/opencv-python

也可以在pip安装的时候拿到下载链接，然后wget下载

https://mirror.baidu.com/pypi/packages/25/72/da7c69a3542071bf1e8f65336721b8b2659194425438d988f79bc14ed9cc/opencv-python-4.9.0.80.tar.gz

解压源代码：

tar -xzvf opencv-python-4.9.0.80.tar.gz

设置编译多线程:

set MAX_JOBS=8
export MAX_JOBS=8

开始编译

进入 opencv-python-4.9.0.80 目录并编译

cd  opencv-python-4.9.0.80
python setup.py install

编译失败，见后面的记录。

安装FastDeploy

标准流程是cpu安装：pip install numpy opencv-python fastdeploy-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html

我们使用命令

pip install fastdeploy-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html

这样跳过了opencv部分，先把fastdeploy装好了。

推理

Python 推理示例

准备模型和图片

wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz
tar xvf ppyoloe_crn_l_300e_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg

 python推理

# GPU/TensorRT部署参考 examples/vision/detection/paddledetection/python
import cv2
import fastdeploy.vision as visionmodel = vision.detection.PPYOLOE("ppyoloe_crn_l_300e_coco/model.pdmodel","ppyoloe_crn_l_300e_coco/model.pdiparams","ppyoloe_crn_l_300e_coco/infer_cfg.yml")
im = cv2.imread("000000014439.jpg")
result = model.predict(im)
print(result)vis_im = vision.vis_detection(im, result, score_threshold=0.5)
cv2.imwrite("vis_image.jpg", vis_im)

opencv-python这里实在装不上， 用Pillow代替，但是报错：

# GPU/TensorRT部署参考 examples/vision/detection/paddledetection/python
# import cv2
from PIL import Image
import fastdeploy.vision as visionmodel = vision.detection.PPYOLOE("ppyoloe_crn_l_300e_coco/model.pdmodel","ppyoloe_crn_l_300e_coco/model.pdiparams","ppyoloe_crn_l_300e_coco/infer_cfg.yml")
# im = cv2.imread("000000014439.jpg")
im =   Image.open("000000014439.jpg")
result = model.predict(im)
print(result)vis_im = vision.vis_detection(im, result, score_threshold=0.5)
# cv2.imwrite("vis_image.jpg", vis_im)
vis_im.save("vis_image.jpg")

结论：python推理失败

C++推理

预编译环境

Release版本

平台文件说明
Linux x64fastdeploy-linux-x64-1.0.7.tgzg++ 8.2编译产出
Windows x64fastdeploy-win-x64-1.0.7.zipVisual Studio 16 2019编译产出
Mac OSX x64fastdeploy-osx-x86_64-1.0.7.tgzclang++ 10.0.0编译产出

没有FreeBSD的，所以我们要自己编译。

进入FastDeploy目录进行编译：

cd FastDeploy
mkdri build && cd build 
cmake ..
make

可以根据自己cpu的核数x，加上-j 2*x参数 ，如4核cpu  make -j 8

老规矩，编译好之后加入PATH路径，而不是放入/usr/bin目录，以免污染整个系统。

发现目录结构远比想像的要复杂，还是用make install 安装吧 。切换root账户，

cmake .. -DCMAKE_INSTALL_PREFIX=/home/xxx/work/fd
make -j 8 
make install

最终使用的语句是在root账户下，在FastDeploy目录执行：

mkdir build
cd build/
cmake .. -DCMAKE_INSTALL_PREFIX=/home/skywalk/work/fd -DWITH_CAPI=ON
make -j 8
make install # 第一次运行报错，所以把下面的patch库挪到install
mkdir third_libs/install
cp -rf third_libs/patchelf/ third_libs/install/
make install

这里参数漏掉一个D ，加上之后编译不过去，也是就是DWITH_CAPI=ON编译不过去，ENABLE_PADDLE_BACKEND和ENABLE_ORT_BACKEND也都过不去。

把参数全删掉可以过去，但那样就没有用了啊！

结论：编译环境失败

准备图片

wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz
tar xvf ppyoloe_crn_l_300e_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg

推理

源码

// GPU/TensorRT部署参考 examples/vision/detection/paddledetection/cpp
#include "fastdeploy/vision.h"int main(int argc, char* argv[]) {namespace vision = fastdeploy::vision;auto model = vision::detection::PPYOLOE("ppyoloe_crn_l_300e_coco/model.pdmodel","ppyoloe_crn_l_300e_coco/model.pdiparams","ppyoloe_crn_l_300e_coco/infer_cfg.yml");auto im = cv::imread("000000014439.jpg");vision::DetectionResult res;model.Predict(im, &res);auto vis_im = vision::VisDetection(im, res, 0.5);cv::imwrite("vis_image.jpg", vis_im);return 0;
}

把文件保存为infer_demo.c, 用gcc编译报错。

到FastDeploy/examples/runtime/cpp 目录，编译

mkdir build && cd build
cmake .. -DFASTDEPLOY_INSTALL_DIR=/home/skywalk/work/fd
make -j 8

（在没有任何参数的编译出来的环境下）编译出来一个runtime_demo文件，执行直接崩了。

结论

目前fastdeploy在FreeBSD没有调通。当然在linux下是极其好用的。

调试

pip install opencv-python报错

搞不定，下载源代码手动编译安装python setup.py install

编译时报错 No module named 'skbuild'

  File "/usr/home/skywalk/work/opencv-python-headless-4.9.0.80/setup.py", line 10, in <module>
    from skbuild import cmaker, setup
ModuleNotFoundError: No module named 'skbuild'

pip install scikit-build

编译安装时报错

[ 31%] Building CXX object modules/dnn/CMakeFiles/opencv_dnn.dir/misc/caffe/opencv-caffe.pb.cc.o
In file included from /usr/home/skywalk/work/opencv-python-4.9.0.80/opencv/modules/dnn/misc/caffe/opencv-caffe.pb.cc:4:
In file included from /usr/home/skywalk/work/opencv-python-4.9.0.80/opencv/modules/dnn/misc/caffe/opencv-caffe.pb.h:10:
/usr/local/include/google/protobuf/port_def.inc:210:1: error: static_assert failed due to requirement '201103L >= 201402L' "Protobuf only supports C++14 and newer."
static_assert(PROTOBUF_CPLUSPLUS_MIN(201402L), "Protobuf only supports C++14 and newer.");
^             ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from /usr/home/skywalk/work/opencv-python-4.9.0.80/opencv/modules/dnn/misc/caffe/opencv-caffe.pb.cc:4:
/usr/home/skywalk/work/opencv-python-4.9.0.80/opencv/modules/dnn/misc/caffe/opencv-caffe.pb.h:17:2: error: This file was generated by an older version of protoc which is
#error This file was generated by an older version of protoc which is
 ^
/usr/home/skywalk/work/opencv-python-4.9.0.80/opencv/modules/dnn/misc/caffe/opencv-caffe.pb.h:18:2: error: incompatible with your Protocol Buffer headers. Please
#error incompatible with your Protocol Buffer headers. Please
  pip install protobuf==3.20试试

不行，用opencv-python4.4.

到openv目录 手工cmke .. make -j 报错

/usr/local/include/absl/strings/internal/has_absl_stringify.h:46:8: error: no template named 'enable_if_t' in namespace 'std'; did you mean simply 'enable_if_t'?
    T, std::enable_if_t<std::is_void<decltype(AbslStringify(
       ^~~~~
[  2%] Built target gen_opencv_python_source
/usr/local/include/absl/meta/type_traits.h:656:1: note: 'enable_if_t' declared here
using enable_if_t = typename std::enable_if<B, T>::type;
^
[  2%] Building CXX object 3rdparty/protobuf/CMakeFiles/libprotobuf.dir/src/google/protobuf/generated_message_table_driven_lite.cc.o
In file included from /home/skywalk/work/opencv-python-4.4.0.42/opencv/3rdparty/protobuf/src/google/protobuf/arena.cc:31:
In file included from /usr/local/include/google/protobuf/arena.h:53:
In file included from /usr/local/include/google/protobuf/arena_align.h:85:
/usr/local/include/google/protobuf/port_def.inc:210:1: error: static_assert failed due to requirement '201103L >= 201402L' "Protobuf only supports C++14 and newer."
static_assert(PROTOBUF_CPLUSPLUS_MIN(201402L), "Protobuf only supports C++14 and newer.");

尝试升级gcc：pkg upgrade gcc,但是也只升级到gcc13 还是不到14

尝试使用opencv-python3.4.17版本

报错

[ 45%] Building CXX object modules/dnn/CMakeFiles/opencv_dnn.dir/misc/caffe/opencv-caffe.pb.cc.o
In file included from /usr/home/skywalk/work/opencv-python-3.4.17.63/opencv/modules/dnn/misc/caffe/opencv-caffe.pb.cc:4:
/usr/home/skywalk/work/opencv-python-3.4.17.63/opencv/modules/dnn/misc/caffe/opencv-caffe.pb.h:17:2: error: This file was generated by an older version of protoc which is
#error This file was generated by an older version of protoc which is
 ^
/usr/home/skywalk/work/opencv-python-3.4.17.63/opencv/modules/dnn/misc/caffe/opencv-caffe.pb.h:18:2: error: incompatible with your Protocol Buffer headers.  Please
#error incompatible with your Protocol Buffer headers.  Please
 ^
/usr/home/skywalk/work/opencv-python-3.4.17.63/opencv/modules/dnn/misc/caffe/opencv-caffe.pb.h:19:2: error: regenerate this file with a newer version of protoc.
#error regenerate this file with a newer version of protoc.

搞不定。

不过可喜的是，

import cv2没有报错，也就是opencv可以用啊！

后来测试，发现不行

编译opencv-python-headless报错

In file included from /usr/home/skywalk/work/opencv-python-headless-4.9.0.80/opencv/modules/dnn/misc/caffe/opencv-caffe.pb.cc:4:
In file included from /usr/home/skywalk/work/opencv-python-headless-4.9.0.80/opencv/modules/dnn/misc/caffe/opencv-caffe.pb.h:10:
/usr/local/include/google/protobuf/port_def.inc:210:1: error: static_assert failed due to requirement '201103L >= 201402L' "Protobuf only supports C++14 and newer."
static_assert(PROTOBUF_CPLUSPLUS_MIN(201402L), "Protobuf only supports C++14 and newer.");
^             ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

在root账户下fastdeploy c编译，make install 报错

-- Installing: /root/work/fd/include/fastdeploy/utils/path.h
CMake Error at cmake_install.cmake:81 (file):
  file INSTALL cannot find
  "/home/skywalk/github/FastDeploy/build/third_libs/install": No such file or
  directory.

尝试

cd ~/github/FastDeploy/build/third_libs

mkdir install
cp -rf patchelf/ install/
然后再make install

c推理例子编译报错：

skywalk@x250:~/github/FastDeploy/examples/runtime/cpp % gcc infer_demo.cc
In file included from /usr/local/include/fastdeploy/vision/visualize/visualize.h:17,
                 from /usr/local/include/fastdeploy/vision.h:78,
                 from infer_demo.cc:2:
/usr/local/include/fastdeploy/vision/common/result.h:16:10: fatal error: opencv2/core/core.hpp: No such file or directory
   16 | #include "opencv2/core/core.hpp"
      |          ^~~~~~~~~~~~~~~~~~~~~~~
compilation terminated.
skywalk@x250:~/github/FastDeploy/examples/runtime/cpp %

examples/runtime/cpp目录编译生成的demo 文件runtime_demo执行报错：

./runtime_demo
[ERROR] fastdeploy/runtime/runtime.cc(105)::AutoSelectBackend    The candiate backends for ModelFormat::PADDLE & Device::CPU are [ Backend::PDINFER ,Backend::PDLITE ,Backend::ORT ,Backend::OPENVINO ], but both of them have not been compiled with current FastDeploy yet.
Assertion failed: (runtime.Init(runtime_option)), function main, file /home/skywalk/github/FastDeploy/examples/runtime/cpp/infer_paddle_paddle_inference.cc, line 37.
Abort (core dumped)

fastdeploy编译报错'opencv2/imgcodecs.hpp' file not found

type.cc.o
/home/skywalk/github/FastDeploy/c_api/fastdeploy_capi/core/fd_type.cc:17:10: fatal error: 'opencv2/imgcodecs.hpp' file not found
#include <opencv2/imgcodecs.hpp>
         ^~~~~~~~~~~~~~~~~~~~~~~

用Pillow替代opencv推理报错

python inf.py
Traceback (most recent call last):
  File "/usr/home/skywalk/py310/lib/python3.10/site-packages/fastdeploy_python-0.0.0-py3.10-freebsd-13.2-RELEASE-amd64.egg/fastdeploy/c_lib_wrap.py", line 164, in <module>
    from .libs.fastdeploy_main import *
ImportError: Shared object "libdl.so.2" not found, required by "libonnxruntime.so.1.12.0"

During handling of the above exception, another exception occurred:

先搁置。

这篇关于编译安装飞桨fastdeploy@FreeBSD（失败）的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！


http://www.chinasem.cn/article/848314。

相关文章

ESP32 esp-idf esp-adf环境安装及.a库创建与编译

ESP32 esp-idf esp-adf环境安装及.a库创建与编译

简介 ESP32 功能丰富的 Wi-Fi & 蓝牙 MCU, 适用于多样的物联网应用。使用freertos操作系统。 ESP-IDF 官方物联网开发框架。 ESP-ADF 官方音频开发框架。 文档参照 https://espressif-docs.readthedocs-hosted.com/projects/esp-adf/zh-cn/latest/get-started/index
阅读更多...
Linux 安装、配置Tomcat 的HTTPS

Linux 安装、配置Tomcat 的HTTPS

Linux 安装 、配置Tomcat的HTTPS 安装Tomcat 这里选择的是 tomcat 10.X ,需要Java 11及更高版本 Binary Distributions ->Core->选择 tar.gz包 下载、上传到内网服务器 /opt 目录tar -xzf 解压将解压的根目录改名为 tomat-10 并移动到 /opt 下, 形成个人习惯的路径 /opt/tomcat-10
阅读更多...
C++工程编译链接错误汇总VisualStudio

C++工程编译链接错误汇总VisualStudio

目录 一些小的知识点 make工具 可以使用windows下的事件查看器崩溃的地方 dumpbin工具查看dll是32位还是64位的 _MSC_VER .cc 和.cpp 【VC++目录中的包含目录】 vs 【C/C++常规中的附加包含目录】——头文件所在目录如何怎么添加，添加了以后搜索头文件就会到这些个路径下搜索了 include<> 和 include"" WinMain 和
阅读更多...
C/C++的编译和链接过程

C/C++的编译和链接过程

目录 从源文件生成可执行文件（书中第2章） 1.Preprocessing预处理——预处理器cpp 2.Compilation编译——编译器cll ps：vs中优化选项设置 3.Assembly汇编——汇编器as ps：vs中汇编输出文件设置 4.Linking链接——链接器ld 符号 模块，库 链接过程——链接器 链接过程 1.简单链接的例子 2.链接过程 3.地址和
阅读更多...
VMware9.0详细安装

VMware9.0详细安装

双击VMware-workstation-full-9.0.0-812388.exe文件： 直接点Next; 这里，我选择了Typical（标准安装）。 因为服务器上只要C盘，所以我选择安装在C盘下的vmware文件夹下面，然后点击Next; 这里我把√取消了，每次启动不检查更新。然后Next； 点击Next； 创建快捷方式等，点击Next； 继续Cont
阅读更多...
vcpkg安装opencv中的特殊问题记录（无法找到opencv_corexd.dll）

vcpkg安装opencv中的特殊问题记录（无法找到opencv_corexd.dll）

我是按照网上的vcpkg安装opencv方法进行的（比如这篇：从0开始在visual studio上安装opencv（超详细，针对小白）），但是中间出现了一些别人没有遇到的问题，虽然原因没有找到，但是本人给出一些暂时的解决办法： 问题1： 我在安装库命令行使用的是 .\vcpkg.exe install opencv 我的电脑是x64，vcpkg在这条命令后默认下载的也是opencv2:x6
阅读更多...
Windwos +vs 2022 编译openssl 1.0.2 库

Windwos +vs 2022 编译openssl 1.0.2 库

一 前言 先说 结论，编译64位报错，查了一圈没找到解决方案，最后换了32位的。 使用qt访问web接口，因为是https，没有openssl库会报错 QNetworkReply* reply = qobject_cast<QNetworkReply*>(sender());if (reply){if (reply->error() == QNetworkReply::NoError
阅读更多...
【服务器运维】CentOS6 minimal 离线安装MySQL5.7

【服务器运维】CentOS6 minimal 离线安装MySQL5.7

1.准备安装包（版本因人而异，所以下面的命令中版本省略，实际操作中用Tab自动补全就好了） cloog-ppl-0.15.7-1.2.el6.x86_64.rpmcpp-4.4.7-23.el6.x86_64.rpmgcc-4.4.7-23.el6.x86_64.rpmgcc-c++-4.4.7-23.el6.x86_64.rpmglibc-2.12-1.212.el6.x86_64.r
阅读更多...
【服务器运维】CentOS7 minimal 离线安装 gcc perl vmware-tools

【服务器运维】CentOS7 minimal 离线安装 gcc perl vmware-tools

0. 本机在有网的情况下，下载CentOS镜像 https://www.centos.org/download/ 1. 取出rpm 有的情况可能不需要net-tools，但是如果出现跟ifconfig相关的错误，就把它安装上。另外如果不想升级内核版本的话，就找对应内核版本的rpm版本安装 perl-Time-Local-1.2300-2.el7.noarch.rpmperl-Tim
阅读更多...
Windows/macOS/Linux 安装 Redis 和 Redis Desktop Manager 可视化工具

Windows/macOS/Linux 安装 Redis 和 Redis Desktop Manager 可视化工具

本文所有安装都在macOS High Sierra 10.13.4进行，Windows安装相对容易些，Linux安装与macOS类似，文中会做区分讲解 1. Redis安装 1.下载Redis https://redis.io/download 把下载的源码更名为redis-4.0.9-source，我喜欢跟maven、Tomcat放在一起，就放到/Users/zhan/Documents
阅读更多...

Copyright China编程 23002807@qq.com

沪ICP备2023033072号-2