!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|https://ai.intel.com/intel-neural-compute-stick-2-smarter-faster-plug-and-play-ai-at-the-edge/]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.