IEI Technology Mustang-V100-MX4, User Manual

Page: 70 / 101

Mustang-V100-MX4
Page 62
\models\FP32\classification\squeezenet\1.1\caffe\squeezenet1
.1.caffemodel" --data_type FP16 --output_dir
"C:\Users<username>\Documents\squeezenet1.1_FP16"
3. The
squeezenet1.1.labels
file contains the classes that ImageNet uses. This
file is included so that the inference results show text instead of classification
numbers. Copy
squeezenet1.1.labels
to your optimized model location:
copy
"C:\Users<username>\Documents\Intel\OpenVINO\openvino_models
\ir\FP32\classification\squeezenet\1.1\caffe\squeezenet1.1.l
abels" "C:\Users<username>\Documents\squeezenet1.1_FP16"
Now your neural network setup is complete and you're ready to run the sample application.
1. Go to modify device number of VPU from 8 to 2, in C:\Program Files
(x86)\IntelSWtools\openvino_<version>\
deployment_tools\inference_engine
\external\hddl\config\hddl_autoboot.config
2. Run the sample executable with specifying the car.png file from the demo directory as
an input image, the IR of your FP16 model and a plugin for a hardware device to
perform inference on.