サンプルを片っ端から実行していくシリーズ。今回はhello_query_deviceのサンプルを実行してみます。実行結果が長いので記事はOS別に記載します。
サンプルは以下のフォルダになります。openvino\inference_engine\samples\python\hello_query_device
実行の前に
サンプルを実行する前に、READMEファイルを確認しておきましょう。このサンプルはOpenVINOで使用出来るデバイスの情報を取得するものなので凄くシンプルです。
モデル
今回のサンプルはモデルは不要です。
環境
以下の環境で確認しました。
MacBook Pro (13-inch, 2018, Four Thunderbolt 3 Ports) プロセッサ 2.7 GHz クアッドコアIntel Core i7 メモリ 16 GB 2133 MHz LPDDR3 グラフィックス Intel Iris Plus Graphics 655 1536 MB
実行
環境変数の設定をしていない場合は、コマンドラインで以下を実行します。/opt/intel/openvino/bin/setupvars.sh
以下のコマンドでhello_query_deviceを実行します。
cd /opt/intel/openvino/deployment_tools/inference_engine/samples/python/hello_query_device
% python3 hello_query_device.py
実行結果例（NCS2無し）
Available devices: Device: CPU Metrics: AVAILABLE_DEVICES: SUPPORTED_METRICS: AVAILABLE_DEVICES, SUPPORTED_METRICS, FULL_DEVICE_NAME, OPTIMIZATION_CAPABILITIES, SUPPORTED_CONFIG_KEYS, RANGE_FOR_ASYNC_INFER_REQUESTS, RANGE_FOR_STREAMS FULL_DEVICE_NAME: Intel(R) Core(TM) i7-8559U CPU @ 2.70GHz OPTIMIZATION_CAPABILITIES: FP32, INT8, BIN SUPPORTED_CONFIG_KEYS: CPU_BIND_THREAD, CPU_THREADS_NUM, CPU_THROUGHPUT_STREAMS, DUMP_EXEC_GRAPH_AS_DOT, DYN_BATCH_ENABLED, DYN_BATCH_LIMIT, EXCLUSIVE_ASYNC_REQUESTS, PERF_COUNT RANGE_FOR_ASYNC_INFER_REQUESTS: 1, 1, 1 RANGE_FOR_STREAMS: 1, 8 Default values for device configuration keys: CPU_BIND_THREAD: NUMA CPU_THREADS_NUM: 0 CPU_THROUGHPUT_STREAMS: 1 DUMP_EXEC_GRAPH_AS_DOT: DYN_BATCH_ENABLED: NO DYN_BATCH_LIMIT: 0 EXCLUSIVE_ASYNC_REQUESTS: NO PERF_COUNT: NO
実行結果例（NCS2 １本）
Available devices: Device: CPU Metrics: AVAILABLE_DEVICES: SUPPORTED_METRICS: AVAILABLE_DEVICES, SUPPORTED_METRICS, FULL_DEVICE_NAME, OPTIMIZATION_CAPABILITIES, SUPPORTED_CONFIG_KEYS, RANGE_FOR_ASYNC_INFER_REQUESTS, RANGE_FOR_STREAMS FULL_DEVICE_NAME: Intel(R) Core(TM) i7-8559U CPU @ 2.70GHz OPTIMIZATION_CAPABILITIES: FP32, INT8, BIN SUPPORTED_CONFIG_KEYS: CPU_BIND_THREAD, CPU_THREADS_NUM, CPU_THROUGHPUT_STREAMS, DUMP_EXEC_GRAPH_AS_DOT, DYN_BATCH_ENABLED, DYN_BATCH_LIMIT, EXCLUSIVE_ASYNC_REQUESTS, PERF_COUNT RANGE_FOR_ASYNC_INFER_REQUESTS: 1, 1, 1 RANGE_FOR_STREAMS: 1, 8 Default values for device configuration keys: CPU_BIND_THREAD: NUMA CPU_THREADS_NUM: 0 CPU_THROUGHPUT_STREAMS: 1 DUMP_EXEC_GRAPH_AS_DOT: DYN_BATCH_ENABLED: NO DYN_BATCH_LIMIT: 0 EXCLUSIVE_ASYNC_REQUESTS: NO PERF_COUNT: NO Device: MYRIAD Metrics: DEVICE_THERMAL: UNSUPPORTED TYPE SUPPORTED_CONFIG_KEYS: DEVICE_ID, PERF_COUNT, EXCLUSIVE_ASYNC_REQUESTS, VPU_MYRIAD_PLATFORM, VPU_HW_STAGES_OPTIMIZATION, VPU_CUSTOM_LAYERS, VPU_PRINT_RECEIVE_TENSOR_TIME, VPU_MYRIAD_FORCE_RESET, LOG_LEVEL, CONFIG_FILE, VPU_IGNORE_IR_STATISTIC RANGE_FOR_ASYNC_INFER_REQUESTS: 3, 6, 1 OPTIMIZATION_CAPABILITIES: FP16 SUPPORTED_METRICS: DEVICE_THERMAL, SUPPORTED_CONFIG_KEYS, RANGE_FOR_ASYNC_INFER_REQUESTS, OPTIMIZATION_CAPABILITIES, SUPPORTED_METRICS, FULL_DEVICE_NAME, AVAILABLE_DEVICES FULL_DEVICE_NAME: Intel Movidius Myriad X VPU AVAILABLE_DEVICES: 20.1-ma2480 Default values for device configuration keys: DEVICE_ID: PERF_COUNT: OFF EXCLUSIVE_ASYNC_REQUESTS: OFF VPU_MYRIAD_PLATFORM: VPU_HW_STAGES_OPTIMIZATION: ON VPU_CUSTOM_LAYERS: VPU_PRINT_RECEIVE_TENSOR_TIME: OFF VPU_MYRIAD_FORCE_RESET: OFF LOG_LEVEL: LOG_NONE CONFIG_FILE: VPU_IGNORE_IR_STATISTIC: OFF
実行結果例（NCS2 2本）
Available devices: Device: CPU Metrics: AVAILABLE_DEVICES: SUPPORTED_METRICS: AVAILABLE_DEVICES, SUPPORTED_METRICS, FULL_DEVICE_NAME, OPTIMIZATION_CAPABILITIES, SUPPORTED_CONFIG_KEYS, RANGE_FOR_ASYNC_INFER_REQUESTS, RANGE_FOR_STREAMS FULL_DEVICE_NAME: Intel(R) Core(TM) i7-8559U CPU @ 2.70GHz OPTIMIZATION_CAPABILITIES: FP32, INT8, BIN SUPPORTED_CONFIG_KEYS: CPU_BIND_THREAD, CPU_THREADS_NUM, CPU_THROUGHPUT_STREAMS, DUMP_EXEC_GRAPH_AS_DOT, DYN_BATCH_ENABLED, DYN_BATCH_LIMIT, EXCLUSIVE_ASYNC_REQUESTS, PERF_COUNT RANGE_FOR_ASYNC_INFER_REQUESTS: 1, 1, 1 RANGE_FOR_STREAMS: 1, 8 Default values for device configuration keys: CPU_BIND_THREAD: NUMA CPU_THREADS_NUM: 0 CPU_THROUGHPUT_STREAMS: 1 DUMP_EXEC_GRAPH_AS_DOT: DYN_BATCH_ENABLED: NO DYN_BATCH_LIMIT: 0 EXCLUSIVE_ASYNC_REQUESTS: NO PERF_COUNT: NO Device: MYRIAD.20.1-ma2480 Metrics: DEVICE_THERMAL: UNSUPPORTED TYPE SUPPORTED_CONFIG_KEYS: DEVICE_ID, PERF_COUNT, EXCLUSIVE_ASYNC_REQUESTS, VPU_MYRIAD_PLATFORM, VPU_HW_STAGES_OPTIMIZATION, VPU_CUSTOM_LAYERS, VPU_PRINT_RECEIVE_TENSOR_TIME, VPU_MYRIAD_FORCE_RESET, LOG_LEVEL, CONFIG_FILE, VPU_IGNORE_IR_STATISTIC RANGE_FOR_ASYNC_INFER_REQUESTS: 3, 6, 1 OPTIMIZATION_CAPABILITIES: FP16 SUPPORTED_METRICS: DEVICE_THERMAL, SUPPORTED_CONFIG_KEYS, RANGE_FOR_ASYNC_INFER_REQUESTS, OPTIMIZATION_CAPABILITIES, SUPPORTED_METRICS, FULL_DEVICE_NAME, AVAILABLE_DEVICES FULL_DEVICE_NAME: Intel Movidius Myriad X VPU AVAILABLE_DEVICES: 20.1-ma2480, 20.2-ma2480 Default values for device configuration keys: DEVICE_ID: PERF_COUNT: OFF EXCLUSIVE_ASYNC_REQUESTS: OFF VPU_MYRIAD_PLATFORM: VPU_HW_STAGES_OPTIMIZATION: ON VPU_CUSTOM_LAYERS: VPU_PRINT_RECEIVE_TENSOR_TIME: OFF VPU_MYRIAD_FORCE_RESET: OFF LOG_LEVEL: LOG_NONE CONFIG_FILE: VPU_IGNORE_IR_STATISTIC: OFF Device: MYRIAD.20.2-ma2480 Metrics: DEVICE_THERMAL: UNSUPPORTED TYPE SUPPORTED_CONFIG_KEYS: DEVICE_ID, PERF_COUNT, EXCLUSIVE_ASYNC_REQUESTS, VPU_MYRIAD_PLATFORM, VPU_HW_STAGES_OPTIMIZATION, VPU_CUSTOM_LAYERS, VPU_PRINT_RECEIVE_TENSOR_TIME, VPU_MYRIAD_FORCE_RESET, LOG_LEVEL, CONFIG_FILE, VPU_IGNORE_IR_STATISTIC RANGE_FOR_ASYNC_INFER_REQUESTS: 3, 6, 1 OPTIMIZATION_CAPABILITIES: FP16 SUPPORTED_METRICS: DEVICE_THERMAL, SUPPORTED_CONFIG_KEYS, RANGE_FOR_ASYNC_INFER_REQUESTS, OPTIMIZATION_CAPABILITIES, SUPPORTED_METRICS, FULL_DEVICE_NAME, AVAILABLE_DEVICES FULL_DEVICE_NAME: Intel Movidius Myriad X VPU AVAILABLE_DEVICES: 20.1-ma2480, 20.2-ma2480 Default values for device configuration keys: DEVICE_ID: PERF_COUNT: OFF EXCLUSIVE_ASYNC_REQUESTS: OFF VPU_MYRIAD_PLATFORM: VPU_HW_STAGES_OPTIMIZATION: ON VPU_CUSTOM_LAYERS: VPU_PRINT_RECEIVE_TENSOR_TIME: OFF VPU_MYRIAD_FORCE_RESET: OFF LOG_LEVEL: LOG_NONE CONFIG_FILE: VPU_IGNORE_IR_STATISTIC: OFF
NCS2１本と２本での差分を見てみました。ちゃんと２本分出ていますね。
その他
NCS2を２本利用した時に、電力低下のメッセージが表示されました。セルフパワーのUSBハブの出番です。未だお持ちでない方はぜひ購入ください。USB3.0対応の方が良いですね。NCS2も試してみてくださいね。
フリーのITエンジニア（何でも屋さん）。趣味は渓流釣り、サッカー観戦、インラインホッケー、アイスホッケー、RaspberryPiを使った工作など。AI活用に興味があり試行錯誤中です。
