The following experiments are done on an Intel NUC with ubuntu 16.04.
make
Download pre-trained caffmodel , save at location ./models/caffemodels/yolo.caffemodel
mvNCCompile ./models/caffemodels/yolo.prototxt -w ./models/caffemodels/yolo.caffemodel -s 12
There will be a file graph generated as converted models for NCS.
python3 ./detectionExample/Main.py --image ./data/dog.jpg
This loads graph by default and results will be like this:
The result was not optimization , still trying now .