# face_lib_web

**Repository Path**: god007/face_lib_web

## Basic Information

- **Project Name**: face_lib_web
- **Description**: 基于云创大数据开源的人脸识别模型，使用tornado开发的python web 人脸识别服务，人脸注册、人脸匹配、建立人脸库
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2019-09-04
- **Last Updated**: 2021-03-17

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# face_lib_web

#### 介绍
基于云创大数据开源的人脸识别模型，使用tornado开发的python web 人脸识别服务，人脸注册、人脸匹配、建立人脸库

##  1.环境搭建

- 依赖Python3，确保安装了python3 、pip3 、git 等工具

- dlib 工具包安装

```
git clone https://github.com/anan91/Dlib-master

cd Dlib-master
```

### 1.1 使用GPU加速 请安装 ubnutu 16.04 (cuda9.0 + cudnn 7.0 + python3.6)

- 安装cuda9.0 + cudnn7.x

- 首先升级python3.5 -> python3.6

```
apt-get install python3.6

rm -rf /usr/bin/python3

ln -s /usr/bin/python3.6 /usr/bin/python3

```
 
- 安装依赖

```
sudo apt-get install python3.6-dev python-setuptools python-numpy libboost-all-dev libopenblas-dev cmake 

```

- pip3安装

```
curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py

python3 get-pip.py
```

- 编译dlib

```
python3 setup.py install --yes USE_AVX_INSTRUCTIONS --yes DLIB_USE_CUDA
```

- scikit-image 工具包安装
```
pip3 install scikit-image
```

查看nvidia驱动状态，处理图片时，执行命令  nvidia-smi 查看gpu状态:
```
root@iZ2ze43cmod4v4omn023lkZ:~# nvidia-smi
Tue Sep  3 14:14:43 2019       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 418.67       Driver Version: 418.67       CUDA Version: 10.1     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  Tesla P4            On   | 00000000:00:07.0 Off |                    0 |
| N/A   29C    P0    23W /  75W |    301MiB /  7611MiB |     23%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|    0     18929      C   python3                                      291MiB |
+-----------------------------------------------------------------------------+

```
###  1.2 没有GPU的环境
- 安装依赖

```
sudo apt-get install python3.6-dev python-setuptools python-numpy cmake 

```
- pip3安装

```
curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py

python3 get-pip.py
```

- scikit-image 工具包安装
```
pip3 install scikit-image
```

- 编译Python所需的dlib
```
cd Dlib-master
python3 setup.py install
```
## 2.环境测试

终端执行命令 python3

```
>>> import dlib;
>>> import skimage;
回车
```
无报错则成功


## 3.项目配置和部署
- 安装依赖
```
pip3 install -r requirements.txt

```
- 修改 settings.py 内的配置：
```
#人脸库存储目录
FACE_LIB_HOME = "/opt/deploy/face-recognition/data/"
# 配置服务端口
tornado.options.define("port", default="5000", type=int)

```

- 运行
```
python3 run.py
```