5 openVINO 运行其他demo

很简单

1、这句话很重要哦，运行全局变量脚本，否则运行demo会报错哦！

source /opt/intel/openvino/bin/setupvars.sh -pyver 3.5

在编译和运行OpenVINO™应用程序之前，必须更新多个环境变量。运行以下脚本以临时设置环境变量：

source/opt/intel/openvino/bin/setupvars.sh

可选：关闭shell时将删除OpenVINO环境变量。作为选项，您可以永久设置环境变量，如下所示：

1. 打开.bashrc文件，的home下：

vi home/ .bashrc

1. 将此行添加到文件末尾：

source/opt/intel/openvino/bin/setupvars.sh

1. 保存并关闭文件：按Esc键并键入:wq。
2. 要测试您的更改，请打开一个新终端。你会看到[setupvars.sh] OpenVINO environment initialized。

设置环境变量。继续下一部分以配置模型优化程序。

 

2、运行编译完的C++ demo,参数一定要带全哦

C++ demo所在路径/home/root1/inference_engine_samples_build/intel64/Release

cd /home/root1/inference_engine_samples_build/intel64/Release

 

测试用的视频及图片所在路径/opt/intel/openvino/deployment_tools/demo

cd /opt/intel/openvino/deployment_tools/demo

 

模型所在路径 /home/root1/openvino_models/

cd /home/root1/openvino_models/

 

人员属性https://docs.openvinotoolkit.org/latest/_inference_engine_samples_crossroad_camera_demo_README.html

./crossroad_camera_demo -d CPU -i /opt/intel/openvino/deployment_tools/demo/out14.avi -m /home/root1/openvino_models/ir/FP32/Security/object_detection/crossroad/0078/dldt/person-vehicle-bike-detection-crossroad-0078.xml -m_pa /home/root1/openvino_models/ir/FP32/Security/object_attributes/pedestrian/person-attributes-recognition-crossroad-0230/dldt/person-attributes-recognition-crossroad-0230.xml -m_reid /home/root1/openvino_models/ir/FP32/Retail/object_reidentification/pedestrian/rmnet_based/0079/dldt/person-reidentification-retail-0079.xml

 

车辆识别https://docs.openvinotoolkit.org/latest/_inference_engine_samples_security_barrier_camera_demo_README.html

./security_barrier_camera_demo

-d CPU -d_va CPU -d_lpr CPU

-i /opt/intel/openvino/deployment_tools/demo/3.jpg

-m /home/root1/openvino_models/ir/FP32/Security/object_detection/barrier/0106/dldt/vehicle-license-plate-detection-barrier-0106.xml

-m_va /home/root1/openvino_models/ir/FP32/Security/object_attributes/vehicle/resnet10_update_1/dldt/vehicle-attributes-recognition-barrier-0039.xml

-m_lpr /home/root1/openvino_models/ir/FP32/Security/optical_character_recognition/license_plate/dldt/license-plate-recognition-barrier-0001.xml

 

人体姿态：

./multi-channel-human-pose-estimation-demo -d CPU -i /opt/intel/openvino/deployment_tools/demo/out.avi -m /home/root1/openvino_models/Transportation/human_pose_estimation/mobilenet-v1/dldt/human-pose-estimation-0001.xml

 

年龄和性别检测：

./interactive_face_detection_demo -i /opt/intel/openvino/deployment_tools/demo/1.mp4 -m /home/root1/openvino_models/Retail/object_detection/face/sqnet1.0modif-ssd/0004/dldt/face-detection-retail-0004.xml -m_ag /home/root1/openvino_models/Retail/object_attributes/age_gender/dldt/age-gender-recognition-retail-0013.xml

 

目标识别https://docs.openvinotoolkit.org/latest/_inference_engine_samples_object_detection_sample_ssd_README.html

只支持图片，两个模型，输出图片结果到demo目录下，目前不知道0013和0002区别在哪？0002使用111.png图片不识别人

./object_detection_sample_ssd -i /opt/intel/openvino/deployment_tools/demo/111.png -m /home/root1/openvino_models/Retail/object_detection/pedestrian/rmnet_ssd/0013/dldt/person-detection-retail-0013.xml -d CPU

 

./object_detection_sample_ssd -i /opt/intel/openvino/deployment_tools/demo/1.png -m /home/root1/openvino_models/Retail/object_detection/pedestrian/hypernet-rfcn/0026/dldt/person-detection-retail-0002.xml -d CPU

 

 

3、运行python demo

python demo所在路径/opt/intel/openvino/inference_engine/samples/python_samples/

cd /opt/intel/openvino/inference_engine/samples/python_samples/

 

图像分类

https://docs.openvinotoolkit.org/latest/_inference_engine_ie_bridges_python_sample_classification_sample_README.html

python3 classification_sample.py -i /cat.bmp -m /alexnet_fp32.xml

python3 classification_sample.py -i /cat.bmp -m /alexnet_fp32.xml -nt 5 -d GPU

 

购物者凝视监视器 https://github.com/intel-iot-devkit/shopper-gaze-monitor-python

cd /opt/intel/openvino/inference_engine/samples/python_samples/shopper-gaze-monitor-python-master

python3 main.py -m /opt/intel/openvino/deployment_tools/tools/model_downloader/Transportation/object_detection/face/pruned_mobilenet_reduced_ssd_shared_weights/dldt/face-detection-adas-0001.xml -pm /opt/intel/openvino/deployment_tools/tools/model_downloader/Transportation/object_attributes/headpose/vanilla_cnn/dldt/head-pose-estimation-adas-0001.xml -l /opt/intel/openvino/inference_engine/lib/intel64/libcpu_extension_sse4.so -d CPU -i resources/face-demographics-walking-and-pause.mp4