Docker下运行openvino人脸识别示例的步骤
(1)获取openvino的软件镜像openvino_docker.tar
2019-08-13 15-49-53.png(2)Docker导入本地镜像为openvino
cat /home/czw/下载/openvino_docker/openvino_docker |docker import - openvino
(3)查看主机上的镜像,找到IMAGE ID
docker images
2019-08-13 15-54-26.png
(4)使用openvino镜像来运行
docker run -it openvino:latest /bin/bash
docker ps -a
使用docker ps -a查看有那些容器在运行
2019-08-13 15-58-48.png(5)再次启动容器需要的操作
docker start 容器ID
docker attach 容器ID
2019-08-13 16-03-25.png
root@7483ae1d61a4:容器已启动标志
之后所有的操作都是在容器内:
2019-08-13 16-05-48.png在容器内时,把它当做linux系统来操作即可
(6)在容器内运行人脸识别示例
main.cpp所在位置:/opt/intel/computer_vision_sdk_2018.3.343/
deployment_tools/inference_engine/samples/interactice_face
_detection_sample
(1)在xx/samples目录下创建名为build的目录
创建build目录:mkdir build
切换到build目录:cd build
(2)编译
cmake -DCMAKE_BUILD_+TYPE=Debug /opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/inference_engine/samples)
运行make生成示例:make
切换到build下的/intel64/Debug目录:
cd /opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/
inference_engine/samples/build/intel64/Debug
(3)输入模型参数,运行示例
./interactive_face_detection_sample -i /opt/image.jpg -m /opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/intel_models/face-detection-adas-0001/FP32/face-detection-adas-0001.xml -m_ag /opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/intel_models/age-gender-recognition-retail-0013/FP32/age-gender-recognition-retail-0013.xml -m_hp /opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/intel_models/head-pose-estimation-adas-0001/FP32/head-pose-estimation-adas-0001.xml -m_em /opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/intel_models/emotions-recognition-retail-0003/FP32/emotions-recognition-retail-0003.xml -d CPU
2019-08-13 16-26-54.png 2019-08-13 16-27-14.png
图像或视频处理后的存储位置: /opt/video/
(4)从容器将文件复制到本机
docker cp 7483ae1d61a4:/opt/video/image.jpg /home/czw/下载