Diary/2018-11-20

NCS2

なぜか，「お昼休みはうきうきハッキング♪あっちもこっちも〜」というフレーズが
頭に浮んでしまって，あのメロディでぐるぐるループ．

ハッキングというわけでもないけど，
Intel Neural Computing Stick 2のデモを試してみた．

用意されているsqueezenet1.1のデモでは，
Core i5-4300U 1.9GHzなノートPCで，MKLDNNPluginなOpenVINOで78.20FPS
なのに対して，
NCS2なmyriadPluginだと106.61FPS
と 1.36倍高速化されるみたい．
ただし，ソフトウェア版はFP32で，NCS2はFP16．

実行ログは次の通り．

###################################################

Run Inference Engine classification sample

Run ./classification_sample -d MYRIAD -i /home/miyo/intel/computer_vision_sdk/deployment_tools/demo/../demo/car.png -m /home/miyo/openvino_models/ir/squeezenet1.1/FP16/squeezenet1.1.xml

[ INFO ] InferenceEngine:
        API version ............ 1.4
        Build .................. 17328
[ INFO ] Parsing input parameters
[ INFO ] Files were added: 1
[ INFO ]     /home/miyo/intel/computer_vision_sdk/deployment_tools/demo/../demo/car.png
[ INFO ] Loading plugin

        API version ............ 1.4
        Build .................. 17328
        Description ....... myriadPlugin
[ INFO ] Loading network files:
        /home/miyo/openvino_models/ir/squeezenet1.1/FP16/squeezenet1.1.xml
        /home/miyo/openvino_models/ir/squeezenet1.1/FP16/squeezenet1.1.bin
[ INFO ] Preparing input blobs
[ WARNING ] Image is resized from (787, 259) to (227, 227)
[ INFO ] Batch size is 1
[ INFO ] Preparing output blobs
[ INFO ] Loading model to the plugin
[ INFO ] Starting inference (1 iterations)
[ INFO ] Processing output blobs

Top 10 results:

Image /home/miyo/intel/computer_vision_sdk/deployment_tools/demo/../demo/car.png

817 0.8295898 label sports car, sport car
511 0.0961304 label convertible
479 0.0439453 label car wheel
751 0.0101318 label racer, race car, racing car
436 0.0074234 label beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon
656 0.0042267 label minivan
586 0.0029869 label half track
717 0.0018148 label pickup, pickup truck
864 0.0013924 label tow truck, tow car, wrecker
581 0.0006595 label grille, radiator grille


total inference time: 9.3803108
Average running time of one iteration: 9.3803108 ms

Throughput: 106.6062761 FPS

[ INFO ] Execution successful


###################################################

Demo completed successfully.