DeepFace【部署 03】轻量级人脸识别和面部属性分析框架deepface在Linux环境下服务部署（conda虚拟环境+docker）

Linux环境下服务部署

1.使用虚拟环境 $810ms$
- [1.1 环境部署](#1.1 环境部署)
- [1.2 服务启动](#1.2 服务启动)
2.使用Docker $680ms$

1.使用虚拟环境 $810ms$

1.1 环境部署

Anaconda的安装步骤这里不再介绍，直接开始使用。

bash 复制代码

# 1.创建虚拟环境
conda create -n deepface python=3.9.18

# 2.激活虚拟环境
conda activate deepface

# 3.安装deepface
pip install deepface -i https://pypi.tuna.tsinghua.edu.cn/simple

以下操作在虚拟环境deepface下执行：

bash 复制代码

# 1.安装mesa-libGL.x86_64
yum install mesa-libGL.x86_64
# 防止报错
ImportError: libGL.so.1: cannot open shared object file: No such file or directory

# 2.安装deprecated
pip install deprecated==1.2.13
# 防止报错
ModuleNotFoundError: No module named 'deprecated'

使用yum install mesa-libGL.x86_64命令会在Linux系统中安装mesa-libGL包。这个包包含了Mesa 3D图形库的运行时库和DRI驱动。安装mesa-libGL包后，系统将能够支持OpenGL，这是一种用于渲染2D和3D矢量图形的跨语言、跨平台的应用程序编程接口（API）。

1.2 服务启动

DeepFace serves an API as well. You can clone [/api](https://github.com/serengil/deepface/tree/master/api) folder and run the api via gunicorn server. This will get a rest service up. In this way, you can call deepface from an external system such as mobile app or web.

bash 复制代码

cd scripts
./service.sh

Linux系统使用这个命令是前台启动，实际的启动用的是shell脚本，内容如下：

shell 复制代码

#!/bin/bash
nohup python -u ./api/api.py > ./deepfacelog.out 2>&1 &

Face recognition, facial attribute analysis and vector representation functions are covered in the API. You are expected to call these functions as http post methods. Default service endpoints will be http://localhost:5000/verify for face recognition, http://localhost:detector_backend for facial attribute analysis, and http://localhost:5000/represent for vector representation. You can pass input images as exact image paths on your environment, base64 encoded strings or images on web. Here, you can find a postman project to find out how these methods should be called.

这里仅贴出如何传递base64进行接口调用：

json 复制代码

{
    "img_path": "data:image/,image_base64_str"
}

仅看一下base64相关源码：

python 复制代码

def load_image(img):
    # The image is a base64 string
    if img.startswith("data:image/"):
        return loadBase64Img(img)

def loadBase64Img(uri):
    encoded_data = uri.split(",")[1]
    nparr = np.fromstring(base64.b64decode(encoded_data), np.uint8)
    img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
    return img

2.使用Docker $680ms$

You can deploy the deepface api on a kubernetes cluster with docker. The following shell script will serve deepface on localhost:5000. You need to re-configure the Dockerfile if you want to change the port. Then, even if you do not have a development environment, you will be able to consume deepface services such as verify and analyze. You can also access the inside of the docker image to run deepface related commands. Please follow the instructions in the shell script.

修改Dockerfile，调整镜像库：

bash 复制代码

# base image
FROM python:3.8
LABEL org.opencontainers.image.source https://github.com/serengil/deepface
# -----------------------------------
# create required folder
RUN mkdir /app
RUN mkdir /app/deepface
# -----------------------------------
# Copy required files from repo into image
COPY ./deepface /app/deepface
COPY ./api/app.py /app/
COPY ./api/routes.py /app/
COPY ./api/service.py /app/
COPY ./requirements.txt /app/
COPY ./setup.py /app/
COPY ./README.md /app/
# -----------------------------------
# switch to application directory
WORKDIR /app
# -----------------------------------
# update image os
RUN apt-get update
RUN apt-get install ffmpeg libsm6 libxext6 -y
# -----------------------------------
# if you will use gpu, then you should install tensorflow-gpu package
# RUN pip install --trusted-host pypi.org --trusted-host pypi.python.org --trusted-host=files.pythonhosted.org tensorflow-gpu
# -----------------------------------
# install deepface from pypi release (might be out-of-the-date)
RUN pip install deepface -i https://pypi.tuna.tsinghua.edu.cn/simple
# -----------------------------------
# environment variables
ENV PYTHONUNBUFFERED=1
# -----------------------------------
# run the app (re-configure port if necessary)
EXPOSE 5000
CMD ["gunicorn", "--workers=1", "--timeout=3600", "--bind=0.0.0.0:5000", "app:create_app()"]

官网启动命令:

shell 复制代码

cd scripts
./dockerize.sh

报错：

bash 复制代码

unable to prepare context: unable to evaluate symlinks in Dockerfile path: lstat /home/deepface/scripts/Dockerfile: no such file or directory
Unable to find image 'deepface:latest' locally
docker: Error response from daemon: pull access denied for deepface, repository does not exist or may require 'docker login': denied: requested access to the resource is denied.
See 'docker run --help'.

解决【不要 cd scripts】原因是执行脚本的文件夹要跟构建镜像使用的Dockerfile同级：

bash 复制代码

./scripts/dockerize.sh
# 这个过程一共有两个步骤：1是构建镜像；2是启动容器。构建镜像的速度取决于网速【时间可能会比较久】

分解步骤：

bash 复制代码

# 构建镜像
docker build -t deepface_image .

# 创建模型文件夹【并将下载好的模型文件上传】
mkdir -p /root/.deepface/weights/

# 启动容器
docker run --name deepface --privileged=true --restart=always --net="host" -v /root/.deepface/weights/:/root/.deepface/weights/ -d deepface_image

DeepFace【部署 03】轻量级人脸识别和面部属性分析框架deepface在Linux环境下服务部署（conda虚拟环境+docker）

Linux环境下服务部署

1.使用虚拟环境810ms

1.1 环境部署

1.2 服务启动

2.使用Docker680ms

1.使用虚拟环境 $810ms$

2.使用Docker $680ms$