YOLO11 ã®å±éãªãã·ã§ã³ã«ã€ããŠç解ããã
ã¯ããã«
ããªãã¯YOLO11 ã䜿ã£ãŠãé·ãéã®ããæ©ãã§ããŸãããç±å¿ã«ããŒã¿ãåéãã綿å¯ã«æ³šéãä»ããã«ã¹ã¿ã YOLO11 ã¢ãã«ããã¬ãŒãã³ã°ããå³å¯ã«è©äŸ¡ããããã«æéãè²»ãããŠããŸããããããŠä»ãããªãã®ã¢ãã«ãç¹å®ã®ã¢ããªã±ãŒã·ã§ã³ããŠãŒã¹ã±ãŒã¹ããããžã§ã¯ãã«æŽ»çšãããšããæ¥ãŸãããããããããªãã®åã«ç«ã¡ã¯ã ããé倧ãªæ±ºæããããŸããããã¯ãããªãã®ã¢ãã«ãã©ã®ããã«ãšã¯ã¹ããŒãããå¹æçã«å±éããããšããããšã§ãã
ãã®ã¬ã€ãã§ã¯ãYOLO11 ã®å±éãªãã·ã§ã³ãšããããžã§ã¯ãã«é©ãããªãã·ã§ã³ãéžæããããã«èæ ®ãã¹ãéèŠãªèŠçŽ ã«ã€ããŠèª¬æããŸãã
YOLO11 ã¢ãã«ã«é©ããé åãªãã·ã§ã³ã®éžã³æ¹
YOLO11 ã¢ãã«ã®ãããã€ãè¡ããšããé©åãªãšã¯ã¹ããŒããã©ãŒããããéžæããããšã¯éåžžã«éèŠã§ããUltralytics YOLO11 Modes ããã¥ã¡ã³ãã«æŠèª¬ãããŠããããã«ãmodel.export()é¢æ°ã¯ãåŠç¿ããã¢ãã«ãæ§ã ãªç°å¢ãæ§èœèŠä»¶ã«åãããæ§ã ãªåœ¢åŒã«å€æããããšãã§ããŸãã
çæ³çãªãã©ãŒãããã¯ãã¹ããŒããããŒããŠã§ã¢ã®å¶çŽãçµ±åã®ããããã®ãã©ã³ã¹ãåããªãããã¢ãã«ã®æå³ããéçšç¶æ³ã«ãã£ãŠç°ãªããŸãã次ã®ã»ã¯ã·ã§ã³ã§ã¯ãåãšã¯ã¹ããŒãã»ãªãã·ã§ã³ã詳ããèŠãŠããããããéžæããã¿ã€ãã³ã°ãç解ããŸãã
YOLO11å±éãªãã·ã§ã³
YOLO11 ã®ããŸããŸãªãããã€ã¡ã³ãã»ãªãã·ã§ã³ã«ã€ããŠèª¬æããŸãããããšã¯ã¹ããŒãã®è©³çŽ°ãªæé ã«ã€ããŠã¯ãUltralytics ããã¥ã¡ã³ãã®ãšã¯ã¹ããŒãã®ããŒãžãã芧ãã ããã
PyTorch
PyTorch ã¯ããã£ãŒãã©ãŒãã³ã°ã 人工ç¥èœã®ã¢ããªã±ãŒã·ã§ã³ã«åºã䜿ãããŠãããªãŒãã³ãœãŒã¹ã®æ©æ¢°åŠç¿ã©ã€ãã©ãªã§ãããé«ãæè»æ§ãšã¹ããŒããæäŸããç 究è ãéçºè ã®éã§äººæ°ãåããŠããã
-
ããã©ãŒãã³ã¹ã»ãã³ãããŒã¯ïŒPyTorch ã¯ãã®äœ¿ãããããšæè»æ§ã§ç¥ãããŠãããããã®çµæãããå°éçã§æé©åãããä»ã®ãã¬ãŒã ã¯ãŒã¯ãšæ¯èŒããå Žåãçã®ããã©ãŒãã³ã¹ã«ãããŠè¥å¹²ã®ãã¬ãŒããªããçããå¯èœæ§ãããã
-
äºææ§ãšçµ±åïŒPython ã®æ§ã ãªããŒã¿ãµã€ãšã³ã¹ããã³æ©æ¢°åŠç¿ã©ã€ãã©ãªãšã®åªããäºææ§ãæäŸããŸãã
-
ã³ãã¥ããã£ã»ãµããŒããšãšã³ã·ã¹ãã ïŒæã掻æ°ã®ããã³ãã¥ããã£ã®1ã€ã§ãåŠç¿ããã©ãã«ã·ã¥ãŒãã£ã³ã°ã®ããã®è±å¯ãªãªãœãŒã¹ããããŸãã
-
ã±ãŒã¹ã¹ã¿ãã£ïŒç 究ãããã¿ã€ãã§ãã䜿ãããå€ãã®åŠè¡è«æã¯PyTorch ã§å±éãããã¢ãã«ãåç §ããŠããã
-
ã¡ã³ããã³ã¹ãšã¢ããããŒãïŒç©æ¥µçãªéçºãšæ°æ©èœã®ãµããŒãã«ããå®æçãªã¢ããããŒãã
-
ã»ãã¥ãªãã£ã«é¢ããèæ ®äºé ïŒã»ãã¥ãªãã£äžã®åé¡ã«å¯ŸããŠã¯å®æçã«ããããåœãŠãããã»ãã¥ãªãã£ã¯å°å ¥ç°å¢å šäœã«å€§ããå·Šå³ãããã
-
ããŒããŠã§ã¢ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ïŒã¢ãã«ã®ãã¬ãŒãã³ã°ãæšè«ãé«éåããããã«äžå¯æ¬ ãªãGPU ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³çšã®CUDA ããµããŒãã
TorchScript
TorchScript C++ ã©ã³ã¿ã€ã ç°å¢ã§å®è¡ããã¢ãã«ã®ãšã¯ã¹ããŒããå¯èœã«ããããšã§ãPyTorch ã®æ©èœãæ¡åŒµããŠãããããã«ãããPython ãå©çšã§ããªãæ¬çªç°å¢ã«é©ããŠããã
-
ããã©ãŒãã³ã¹ã»ãã³ãããŒã¯ïŒç¹ã«æ¬çªç°å¢ã§ã¯ããã€ãã£ãPyTorch ãããããã©ãŒãã³ã¹ãåäžãããããšãã§ããã
-
äºææ§ãšçµ±åïŒPyTorch ãã C++ ãããã¯ã·ã§ã³ç°å¢ãžã·ãŒã ã¬ã¹ã«ç§»è¡ã§ããããã«èšèšãããŠããŸãããäžéšã®é«åºŠãªæ©èœã¯å®å šã«ã¯ç§»è¡ã§ããªãå ŽåããããŸãã
-
ã³ãã¥ããã£ã®ãµããŒããšãšã³ã·ã¹ãã ïŒPyTorch ã®å€§èŠæš¡ã³ãã¥ããã£ã®æ©æµãåããããå°éçãªéçºè ã®ç¯å²ã¯çãã
-
ã±ãŒã¹ã¹ã¿ã㣠Python ã®ããã©ãŒãã³ã¹ã»ãªãŒããŒããããããã«ããã¯ãšãªã£ãŠããç£æ¥ç°å¢ã§åºã䜿çšãããŠããã
-
ã¡ã³ããã³ã¹ãšã¢ããããŒãïŒPyTorch ãäžè²«ããã¢ããããŒããå®æœã
-
ã»ãã¥ãªãã£ãžã®é æ ®ïŒPython ãå®å šã«ã€ã³ã¹ããŒã«ãããŠããªãç°å¢ã§ãã¢ãã«ãå®è¡ã§ããããã«ããããšã§ãã»ãã¥ãªãã£ãåäžãããŸãã
-
ããŒããŠã§ã¢ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ïŒPyTorch ã®CUDA ãµããŒããç¶æ¿ããGPU ã®å¹ççãªå©çšãä¿èšŒããŸãã
ONNX
OpenNeural NetworkExchange (ONNX) ã¯ãç°ãªããã¬ãŒã ã¯ãŒã¯éã§ã®ã¢ãã«ã®çžäºéçšæ§ãå¯èœã«ãããã©ãŒãããã§ãããæ§ã ãªãã©ãããã©ãŒã ã«å±éããéã«éèŠãšãªãã
-
ããã©ãŒãã³ã¹ã»ãã³ãããŒã¯ïŒONNX ã¢ãã«ã¯ãå°å ¥ãããã©ã³ã¿ã€ã ã«ãã£ãŠããã©ãŒãã³ã¹ãå€ããå¯èœæ§ããããŸãã
-
äºææ§ãšçµ±åïŒãã¬ãŒã ã¯ãŒã¯ã«ãšããããªãæ§è³ªã«ãããè€æ°ã®ãã©ãããã©ãŒã ãããŒããŠã§ã¢ã«ãŸãããé«ãçžäºéçšæ§ã
-
ã³ãã¥ããã£ã®ãµããŒããšãšã³ã·ã¹ãã ïŒå€ãã®çµç¹ã«ãã£ãŠãµããŒããããå¹ åºããšã³ã·ã¹ãã ãšæé©åã®ããã®ããŸããŸãªããŒã«ã«ã€ãªãã£ãŠããã
-
ã±ãŒã¹ã¹ã¿ãã£ç°ãªãæ©æ¢°åŠç¿ãã¬ãŒã ã¯ãŒã¯éã§ã¢ãã«ã移åãããããã«é »ç¹ã«äœ¿çšããããã®æè»æ§ã瀺ããŠããã
-
ã¡ã³ããã³ã¹ãšã¢ããããŒãïŒãªãŒãã³ã¹ã¿ã³ããŒããšããŠãONNX ã¯å®æçã«ã¢ããããŒããããæ°ãããªãã¬ãŒã·ã§ã³ãã¢ãã«ããµããŒãããŠããã
-
ã»ãã¥ãªãã£ã®èæ ®ïŒä»ã®ã¯ãã¹ãã©ãããã©ãŒã ããŒã«ãšåæ§ã«ãå€æãšãããã€ã®ãã€ãã©ã€ã³ã§å®å šãªãã©ã¯ãã£ã¹ã確ä¿ããããšãäžå¯æ¬ ã§ãã
-
ããŒããŠã§ã¢ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ïŒONNX Runtimeã䜿çšãããšãã¢ãã«ã¯ããŸããŸãªããŒããŠã§ã¢æé©åã掻çšã§ããŸãã
OpenVINO
OpenVINO ã¯ãIntel ããŒããŠã§ã¢å šäœãžã®ãã£ãŒãã©ãŒãã³ã°ã¢ãã«ã®å±éã容æã«ããããã©ãŒãã³ã¹ãšã¹ããŒããåäžãããããã«èšèšãããIntel ããŒã«ãããã§ããã
-
ããã©ãŒãã³ã¹ãã³ãããŒã¯ïŒç¹ã«Intel CPUãGPUãVPUåãã«æé©åãããŠãããäºææ§ã®ããããŒããŠã§ã¢äžã§å€§å¹ ãªããã©ãŒãã³ã¹åäžãå®çŸããŸãã
-
äºææ§ãšçµ±åïŒIntel ã®ãšã³ã·ã¹ãã å ã§æãããæ©èœããããä»ã®ããŸããŸãªãã©ãããã©ãŒã ããµããŒãããŠããã
-
ã³ãã¥ããã£ã®ãµããŒããšãšã³ã·ã¹ãã ïŒIntel ã«æ¯ããããç¹ã«ã³ã³ãã¥ãŒã¿ã»ããžã§ã³ã®åéã§ã¯åŒ·åºãªãŠãŒã¶ãŒã»ããŒã¹ãããã
-
ã±ãŒã¹ã¹ã¿ã㣠Intel ãããŒããŠã§ã¢ãæ®åããŠããIoTããšããžã³ã³ãã¥ãŒãã£ã³ã°ã®ã·ããªãªã§ããå©çšãããã
-
ã¡ã³ããã³ã¹ãšã¢ããããŒãïŒIntel ææ°ã®ãã£ãŒãã©ãŒãã³ã°ã¢ãã«ãšIntel ããŒããŠã§ã¢ããµããŒããããããOpenVINO ãå®æçã«ã¢ããããŒãããŸãã
-
ã»ãã¥ãªãã£ãžã®é æ ®ïŒæ©å¯æ§ã®é«ãã¢ããªã±ãŒã·ã§ã³ã«é©ããå ç¢ãªã»ãã¥ãªãã£æ©èœãæäŸã
-
ããŒããŠã§ã¢ã»ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ïŒå°çšã®åœä»€ã»ãããšããŒããŠã§ã¢æ©èœã掻çšããIntel ããŒããŠã§ã¢ã§ã®ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³çšã«èª¿æŽãããŠããŸãã
OpenVINO ã䜿çšããå±éã®è©³çŽ°ã«ã€ããŠã¯ãUltralytics Integration ã®ããã¥ã¡ã³ããåç §ããŠãã ããïŒIntel OpenVINO ãšã¯ã¹ããŒãã
TensorRT
TensorRT ã¯ãNVIDIA ãæäŸããé«æ§èœãªãã£ãŒãã©ãŒãã³ã°æšè«ãªããã£ãã€ã¶ãšã©ã³ã¿ã€ã ã§ãã¹ããŒããšå¹çãå¿ èŠãšããã¢ããªã±ãŒã·ã§ã³ã«æé©ã§ãã
-
æ§èœãã³ãããŒã¯ïŒé«éæšè«ããµããŒãããNVIDIA GPUäžã§ãããã¯ã©ã¹ã®ããã©ãŒãã³ã¹ãå®çŸã
-
äºææ§ãšçµ±åïŒNVIDIA ããŒããŠã§ã¢ã«æé©ã§ããã®ç°å¢ä»¥å€ã§ã®ãµããŒãã¯éå®çã
-
ã³ãã¥ããã£ã»ãµããŒããšãšã³ã·ã¹ãã ïŒNVIDIA ã®éçºè ãã©ãŒã©ã ãããã¥ã¡ã³ããéãã匷åãªãµããŒããããã¯ãŒã¯ã
-
ã±ãŒã¹ã¹ã¿ãã£ãããªãç»åããŒã¿ã®ãªã¢ã«ã¿ã€ã æšè«ãå¿ èŠãšããæ¥çã§åºãæ¡çšãããŠããã
-
ã¡ã³ããã³ã¹ãšã¢ããããŒã:NVIDIA ã¯ãããã©ãŒãã³ã¹ãåäžãããæ°ããGPU ã¢ãŒããã¯ãã£ããµããŒãããããã«ãé »ç¹ãªã¢ããããŒãã§TensorRT ãç¶æããŸãã
-
ã»ãã¥ãªãã£ãžã®é æ ®ïŒå€ãã®NVIDIA 補åãšåæ§ãã»ãã¥ãªãã£ã«éç¹ã眮ããŠããããå ·äœçãªå 容ã¯å°å ¥ç°å¢ã«äŸåããã
-
ããŒããŠã§ã¢ã»ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ïŒNVIDIA GPUå°çšã«èšèšãããé«åºŠãªæé©åãšé«éåãæäŸããŸãã
CoreML
CoreML ã¯ã¢ããã«ã®æ©æ¢°åŠç¿ãã¬ãŒã ã¯ãŒã¯ã§ãiOS ãmacOSãwatchOSãtvOSãå«ãã¢ããã«ã®ãšã³ã·ã¹ãã ã«ããããªã³ããã€ã¹ã»ããã©ãŒãã³ã¹ã®ããã«æé©åãããŠããã
-
ããã©ãŒãã³ã¹ãã³ãããŒã¯ïŒApple補ããŒããŠã§ã¢ã®ããã€ã¹äžã§ã®ããã©ãŒãã³ã¹ã«æé©åãããããããªãŒã®æ¶è²»ãæå°éã«æããŸãã
-
äºææ§ãšçµ±åïŒAppleã®ãšã³ã·ã¹ãã å°çšã§ãiOS ãmacOSã¢ããªã±ãŒã·ã§ã³ã«åççãªã¯ãŒã¯ãããŒãæäŸããŸãã
-
ã³ãã¥ããã£ã®ãµããŒããšãšã³ã·ã¹ãã ïŒAppleã®åŒ·åãªãµããŒããšç±å¿ãªéçºè ã³ãã¥ããã£ãè±å¯ãªããã¥ã¡ã³ããšããŒã«ã
-
ã±ãŒã¹ã¹ã¿ãã£ã¢ããã«è£œåã®ããã€ã¹äžã§ã®æ©æ¢°åŠç¿æ©èœãå¿ èŠãšããã¢ããªã±ãŒã·ã§ã³ã§ãã䜿çšãããã
-
ã¡ã³ããã³ã¹ãšã¢ããããŒãïŒææ°ã®æ©æ¢°åŠç¿ã®é²æ©ãšAppleã®ããŒããŠã§ã¢ããµããŒãããããã«ãAppleã«ãã£ãŠå®æçã«æŽæ°ãããŸãã
-
ã»ãã¥ãªãã£ãžã®é æ ®ïŒãŠãŒã¶ãŒã®ãã©ã€ãã·ãŒãšããŒã¿ã»ã»ãã¥ãªãã£ã«éç¹ã眮ãã¢ããã«ã®æ©æµã
-
ããŒããŠã§ã¢ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ïŒAppleã®ãã¥ãŒã©ã«ã»ãšã³ãžã³ãšGPU ãæ倧éã«æŽ»çšããæ©æ¢°åŠç¿ã¿ã¹ã¯ãå éã
TF SavedModel
TF SavedModel ã¯ãTensorFlow æ©æ¢°åŠç¿ã¢ãã«ã®ä¿åãšæäŸã®ããã®ãã©ãŒãããã§ãç¹ã«ã¹ã±ãŒã©ãã«ãªãµãŒããŒç°å¢ã«é©ããŠããã
-
ããã©ãŒãã³ã¹ã»ãã³ãããŒã¯ãµãŒããŒç°å¢ã«ãããŠãç¹ã«TensorFlow Servingãšäœµçšããããšã§ãã¹ã±ãŒã©ãã«ãªããã©ãŒãã³ã¹ãæäŸããŸãã
-
äºææ§ãšçµ±åïŒã¯ã©ãŠãããšã³ã¿ãŒãã©ã€ãºãµãŒããŒã®ãããã€ã¡ã³ããå«ããTensorFlow ã®ãšã³ã·ã¹ãã å šäœã«ãããå¹ åºãäºææ§ã
-
ã³ãã¥ããã£ã®ãµããŒããšãšã³ã·ã¹ãã ïŒTensorFlow ã®äººæ°ã«ãã倧èŠæš¡ãªã³ãã¥ããã£ã»ãµããŒãããããã€ãšæé©åã®ããã®èšå€§ãªããŒã«çŸ€ã
-
ã±ãŒã¹ã¹ã¿ãã£ãã£ãŒãã©ãŒãã³ã°ã¢ãã«ã倧èŠæš¡ã«æäŸããããã®æ¬çªç°å¢ã§åºã䜿çšãããŠããã
-
ã¡ã³ããã³ã¹ãšã¢ããããŒãïŒGoogle ãšTensorFlow ã³ãã¥ããã£ã®ãµããŒãã«ãããå®æçãªã¢ããããŒããšæ°æ©èœãä¿èšŒãããŸãã
-
ã»ãã¥ãªãã£ãžã®é æ ®ïŒTensorFlow Servingã䜿çšãããããã€ã¡ã³ãã«ã¯ããšã³ã¿ãŒãã©ã€ãºã»ã°ã¬ãŒãã®ã¢ããªã±ãŒã·ã§ã³ã®ããã®å ç¢ãªã»ãã¥ãªãã£æ©èœãå«ãŸããŠããŸãã
-
ããŒããŠã§ã¢ã»ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ïŒTensorFlow ã®ããã¯ãšã³ããéããŠæ§ã ãªããŒããŠã§ã¢ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ããµããŒãããŸãã
TF GraphDef
TF GraphDef ã¯ãã¢ãã«ãã°ã©ããšããŠè¡šçŸããTensorFlow ãããã¯ãéçãªèšç®ã°ã©ããå¿ èŠãªç°å¢ã«ãšã£ãŠæçãªãã©ãŒãããã§ããã
-
æ§èœãã³ãããŒã¯ïŒäžè²«æ§ãšä¿¡é Œæ§ã«éç¹ã眮ããéçèšç®ã°ã©ãã®å®å®ããããã©ãŒãã³ã¹ãæäŸããŸãã
-
äºææ§ãšçµ±åïŒTensorFlow ã®ã€ã³ãã©ã«ç°¡åã«çµ±åã§ããããSavedModel ãšæ¯ã¹ããšæè»æ§ã«æ¬ ããã
-
ã³ãã¥ããã£ã®ãµããŒããšãšã³ã·ã¹ãã ïŒéçã°ã©ããæé©åããããã®å€ãã®ãªãœãŒã¹ãå©çšå¯èœã§ãTensorFlow ã®ãšã³ã·ã¹ãã ã«ããåªãããµããŒãã
-
ã±ãŒã¹ã¹ã¿ãã£ïŒç¹å®ã®çµã¿èŸŒã¿ã·ã¹ãã ãªã©ãéçãªã°ã©ããå¿ èŠãªã·ããªãªã§åœ¹ç«ã€ã
-
ã¡ã³ããã³ã¹ãšã¢ããããŒãïŒTensorFlow ã®ã³ã¢ã¢ããããŒããšäžŠè¡ããŠãå®æçãªã¢ããããŒããè¡ããŸãã
-
ã»ãã¥ãªãã£ãžã®é æ ®ïŒTensorFlow ã®ç¢ºç«ãããã»ãã¥ãªãã£æ £è¡ã«ãããå®å šãªé åãä¿èšŒããã
-
ããŒããŠã§ã¢ã»ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ïŒSavedModel ã»ã©æè»ã§ã¯ãªãããTensorFlow ã®ããŒããŠã§ã¢ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ãªãã·ã§ã³ãå©çšã§ããã
TF ã©ã€ã
TF Liteã¯ãTensorFlow'ã¢ãã€ã«ããã³çµã¿èŸŒã¿ããã€ã¹ã®æ©æ¢°åŠç¿ã®ããã®ãœãªã¥ãŒã·ã§ã³ã§ããããªã³ããã€ã¹æšè«ã®ããã®è»œéã©ã€ãã©ãªãæäŸããã
-
ããã©ãŒãã³ã¹ã»ãã³ãããŒã¯ïŒã¢ãã€ã«æ©åšãçµã¿èŸŒã¿æ©åšã§ã®ã¹ããŒããšå¹çæ§ãè¿œæ±ããèšèšã
-
äºææ§ãšçµ±åæ§ïŒè»œéã§ãããããæ§ã ãªããã€ã¹ã§äœ¿çšå¯èœã
-
ã³ãã¥ããã£ã»ãµããŒããšãšã³ã·ã¹ãã ïŒGoogle ã匷åºãªã³ãã¥ããã£ããããéçºè åãã®ãªãœãŒã¹ãå¢ããŠããã
-
ã±ãŒã¹ã¹ã¿ãã£æå°éã®ãããããªã³ãã§ããã€ã¹äžã§ã®æšè«ãå¿ èŠãšããã¢ãã€ã«ã¢ããªã±ãŒã·ã§ã³ã«äººæ°ã
-
ã¡ã³ããã³ã¹ãšã¢ããããŒãå®æçãªã¢ããããŒãã«ãããææ°ã®æ©èœãšã¢ãã€ã«ããã€ã¹åãã®æé©åãæäŸããŸãã
-
ã»ãã¥ãªãã£ãžã®é æ ®ïŒãšã³ããŠãŒã¶ãŒããã€ã¹äžã§ã¢ãã«ãå®è¡ããããã®ã»ãã¥ã¢ãªç°å¢ãæäŸããŸãã
-
ããŒããŠã§ã¢ã»ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ïŒGPU ãDSPãªã©ãããŸããŸãªããŒããŠã§ã¢ã»ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ã»ãªãã·ã§ã³ããµããŒãã
TF ãšããžTPU
TF EdgeTPU ã¯ãGoogle ã® EdgeTPU ããŒããŠã§ã¢äžã§é«éãã€å¹ççãªã³ã³ãã¥ãŒãã£ã³ã°ãè¡ãããã«èšèšãããŠããããªã¢ã«ã¿ã€ã åŠçãå¿ èŠãšãã IoT ããã€ã¹ã«æé©ã§ãã
-
æ§èœãã³ãããŒã¯ïŒGoogle's EdgeTPU ããŒããŠã§ã¢ã§ã®é«éã§å¹ççãªã³ã³ãã¥ãŒãã£ã³ã°ã«æé©åãããŠããŸãã
-
äºææ§ãšçµ±åïŒEdgeTPU ããã€ã¹ã®TensorFlow Lite ã¢ãã«ã§ã®ã¿åäœããŸãã
-
ã³ãã¥ããã£ã»ãµããŒããšãšã³ã·ã¹ãã ïŒGoogle ããµãŒãããŒãã£ã®éçºè ãæäŸãããªãœãŒã¹ã§ãµããŒããæ¡å€§ã
-
ã±ãŒã¹ã¹ã¿ãã£äœã¬ã€ãã³ã·ãŒã§ãªã¢ã«ã¿ã€ã åŠçãå¿ èŠãªIoTæ©åšãã¢ããªã±ãŒã·ã§ã³ã«äœ¿çšã
-
ã¡ã³ããã³ã¹ãšã¢ããããŒãïŒæ°ããEdgeTPU ããŒããŠã§ã¢ã»ãªãªãŒã¹ã®æ©èœã掻çšãããããç¶ç¶çã«æ¹è¯ã
-
ã»ãã¥ãªãã£ãžã®é æ ®ïŒGoogle ãIoTããã³ãšããžããã€ã¹åãã®å ç¢ãªã»ãã¥ãªãã£ãšçµ±åã
-
ããŒããŠã§ã¢ã»ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ïŒGoogle Coralããã€ã¹ãæ倧éã«æŽ»çšã§ããããã«ã«ã¹ã¿ã èšèšãããŠããŸãã
TF.js
TensorFlow.js(TF.js)ã¯ãæ©æ¢°åŠç¿æ©èœããã©ãŠã¶ã«çŽæ¥ããããã©ã€ãã©ãªã§ããããŠã§ãéçºè ãšãŠãŒã¶ãŒã«æ°ããªå¯èœæ§ãæäŸãããããã¯ãšã³ãã®ã€ã³ãã©ãå¿ èŠãšããã«ããŠã§ãã¢ããªã±ãŒã·ã§ã³ã«æ©æ¢°åŠç¿ã¢ãã«ãçµ±åããããšãã§ããŸãã
-
ããã©ãŒãã³ã¹ãã³ãããŒã¯ïŒã¯ã©ã€ã¢ã³ãã»ããã€ã¹ã«ããããã劥åœãªããã©ãŒãã³ã¹ã§ããã©ãŠã¶ãŒã§çŽæ¥æ©æ¢°åŠç¿ãå¯èœã
-
äºææ§ãšçµ±åïŒãŠã§ããã¯ãããžãŒãšã®é«ãäºææ§ã«ããããŠã§ãã¢ããªã±ãŒã·ã§ã³ã«ç°¡åã«çµ±åã§ããŸãã
-
ã³ãã¥ããã£ã®ãµããŒããšãšã³ã·ã¹ãã ïŒãŠã§ããšNode.jséçºè ã®ã³ãã¥ããã£ã«ãããµããŒããšãMLã¢ãã«ããã©ãŠã¶ã«ãããã€ããããã®æ§ã ãªããŒã«ã
-
ã±ãŒã¹ã¹ã¿ãã£ãµãŒããŒãµã€ãã®åŠçãå¿ èŠãšãããã¯ã©ã€ã¢ã³ããµã€ãã®æ©æ¢°åŠç¿ã®æ©æµãåããã€ã³ã¿ã©ã¯ãã£ããªãŠã§ãã¢ããªã±ãŒã·ã§ã³ã«æé©ã§ãã
-
ã¡ã³ããã³ã¹ãšæŽæ°ïŒãªãŒãã³ãœãŒã¹ã³ãã¥ããã£ããã®è²¢ç®ã«ãããTensorFlow ããŒã ãã¡ã³ããã³ã¹ãè¡ã£ãŠããŸãã
-
ã»ãã¥ãªãã£ãžã®é æ ®ïŒãŠã§ãã»ãã©ãããã©ãŒã ã®ã»ãã¥ãªãã£ã»ã¢ãã«ãå©çšãããã©ãŠã¶ã®ã»ãã¥ã¢ã»ã³ã³ããã¹ãå ã§å®è¡ãããã
-
ããŒããŠã§ã¢ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ïŒWebGLã®ãããªããŒããŠã§ã¢ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ã«ã¢ã¯ã»ã¹ãããŠã§ãããŒã¹ã®APIã䜿çšããããšã§ãããã©ãŒãã³ã¹ãåäžãããããšãã§ããŸãã
PaddlePaddle
PaddlePaddle ã¯ãçŸåºŠãéçºãããªãŒãã³ãœãŒã¹ã®ãã£ãŒãã©ãŒãã³ã°ãã¬ãŒã ã¯ãŒã¯ã§ãããç 究è ã«ãšã£ãŠã¯å¹ççã§ãéçºè ã«ãšã£ãŠã¯äœ¿ããããããã«èšèšãããŠãããç¹ã«äžåœã§äººæ°ããããäžåœèªåŠçã«ç¹åãããµããŒããæäŸããŠããã
-
ããã©ãŒãã³ã¹ã»ãã³ãããŒã¯äœ¿ãããããšæ¡åŒµæ§ã«éç¹ã眮ãã競äºåã®ããããã©ãŒãã³ã¹ãæäŸã
-
äºææ§ãšçµ±åïŒBaiduã®ãšã³ã·ã¹ãã å ã«ããŸãçµ±åãããå¹ åºãã¢ããªã±ãŒã·ã§ã³ããµããŒãããŠããŸãã
-
ã³ãã¥ããã£ã®ãµããŒããšãšã³ã·ã¹ãã ïŒã³ãã¥ããã£ã¯äžççã«ã¯å°ããããç¹ã«äžåœã§ã¯æ¥éã«æé·ããŠããã
-
ã±ãŒã¹ã¹ã¿ãã£äžåœåžå Žããä»ã®äž»èŠãªãã¬ãŒã ã¯ãŒã¯ã®ä»£æ¿ãæ¢ããŠããéçºè ã«ãã䜿ãããŠããã
-
ã¡ã³ããã³ã¹ãšã¢ããããŒãäžåœèªã®AIã¢ããªã±ãŒã·ã§ã³ãšãµãŒãã¹ã®æäŸãäžå¿ã«å®æçã«æŽæ°ã
-
ã»ãã¥ãªãã£ãžã®é æ ®ïŒããŒã¿ãã©ã€ãã·ãŒãšã»ãã¥ãªãã£ãéèŠããäžåœã®ããŒã¿ã¬ããã³ã¹åºæºã«å¯Ÿå¿ã
-
ããŒããŠã§ã¢ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ïŒãã€ãã¥ç¬èªã®Kunlunããããå«ãæ§ã ãªããŒããŠã§ã¢ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ããµããŒãã
NCNN
NCNN ã¯ãã¢ãã€ã«ãã©ãããã©ãŒã åãã«æé©åãããé«æ§èœãªãã¥ãŒã©ã«ãããã¯ãŒã¯æšè«ãã¬ãŒã ã¯ãŒã¯ã§ããã軜éãã€å¹ççãªç¹ãç¹åŸŽã§ããªãœãŒã¹ãéãããŠããã¢ãã€ã«æ©åšãçµã¿èŸŒã¿æ©åšã«ç¹ã«é©ããŠããã
-
ããã©ãŒãã³ã¹ã»ãã³ãããŒã¯ïŒã¢ãã€ã«ã»ãã©ãããã©ãŒã åãã«é«åºŠã«æé©åãããŠãããARMããŒã¹ã®ããã€ã¹ã§å¹ççãªæšè«ãå¯èœã
-
äºææ§ãšçµ±åïŒæºåž¯é»è©±ãARMã¢ãŒããã¯ãã£ã®çµã¿èŸŒã¿ã·ã¹ãã ã§ã®ã¢ããªã±ãŒã·ã§ã³ã«é©ããŠããŸãã
-
ã³ãã¥ããã£ã®ãµããŒããšãšã³ã·ã¹ãã ïŒã¢ãã€ã«ããã³çµã¿èŸŒã¿MLã¢ããªã±ãŒã·ã§ã³ã«ç¹åããããããã ã掻çºãªã³ãã¥ããã£ã«æ¯ããããŠããã
-
ã±ãŒã¹ã¹ã¿ã㣠Android ããã®ä»ã®ARMããŒã¹ã®ã·ã¹ãã ã§ãå¹çãšã¹ããŒããéèŠãããã¢ãã€ã«ã»ã¢ããªã±ãŒã·ã§ã³ã«é©ããŠããŸãã
-
ã¡ã³ããã³ã¹ãšã¢ããããŒãæ§ã ãªARMããã€ã¹äžã§é«ãããã©ãŒãã³ã¹ãç¶æããããã«ç¶ç¶çã«æ¹è¯ãããŠããŸãã
-
ã»ãã¥ãªãã£ãžã®é æ ®ïŒããã€ã¹äžã§ããŒã«ã«ã«å®è¡ããããšã«éç¹ã眮ããããã€ã¹äžã§ã®åŠçã«åºæã®ã»ãã¥ãªãã£ã掻çšããã
-
ããŒããŠã§ã¢ã»ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ïŒARM CPUããã³GPUåãã«ã«ã¹ã¿ãã€ãºããããããã®ã¢ãŒããã¯ãã£ã«ç¹åããæé©åãæœãããŠããŸãã
MNN
MNNã¯éåžžã«å¹ççã§è»œéãªãã£ãŒãã©ãŒãã³ã°ãã¬ãŒã ã¯ãŒã¯ã§ããããã£ãŒãã©ãŒãã³ã°ã¢ãã«ã®æšè«ãšåŠç¿ããµããŒãããããã€ã¹äžã§ã®æšè«ãšåŠç¿ã«ãããŠæ¥çããªãŒãããããã©ãŒãã³ã¹ãçºæ®ããããŸããMNNã¯IoTãªã©ã®çµã¿èŸŒã¿æ©åšã§ãå©çšãããŠããã
YOLO11 å±éãªãã·ã§ã³ã®æ¯èŒåæ
以äžã®è¡šã¯ãYOLO11 ã¢ãã«ã§å©çšå¯èœãªããŸããŸãªå±éãªãã·ã§ ã³ã®ã¹ãããã·ã§ããã§ãããããã€ãã®éèŠãªåºæºã«åºã¥ããŠããããžã§ã¯ã ããŒãºã«æé©ãªå±éãªãã·ã§ã³ãè©äŸ¡ããã®ã«åœ¹ç«ã¡ãŸããåå±éãªãã·ã§ã³ã®ãã©ãŒãããã«ã€ããŠã®è©³çŽ°ã¯ãUltralytics ããã¥ã¡ã³ãã®ãšã¯ã¹ããŒããã©ãŒãããã®ããŒãžãåç §ããŠãã ããã
å±éãªãã·ã§ã³ | ããã©ãŒãã³ã¹ã»ãã³ãããŒã¯ | äºææ§ãšçµ±å | å°å瀟äŒã®ãµããŒããšãšã³ã·ã¹ãã | ã±ãŒã¹ã¹ã¿ã㣠| ã¡ã³ããã³ã¹ãšã¢ããããŒã | ã»ãã¥ãªãã£ãžã®é æ ® | ããŒããŠã§ã¢ã»ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ |
---|---|---|---|---|---|---|---|
PyTorch | åªããæè»æ§ã | Python ã©ã€ãã©ãªãšã®çžæ§æ矀 | è±å¯ãªãªãœãŒã¹ãšã³ãã¥ãã㣠| ç 究ãšãããã¿ã€ã | å®æçãã€ç©æ¥µçãªéçº | é åç°å¢ã«ãã | CUDA GPU ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³å¯Ÿå¿ |
TorchScript | ãããçç£ã«é©ããŠãããPyTorch | PyTorch ãã C++ ãžã®ã¹ã ãŒãºãªç§»è¡ | å°éæ§ã¯é«ããå¹ ã¯çãPyTorch | Python ãããã«ããã¯ãšãªã£ãŠããæ¥ç | äžè²«ããã¢ããããŒãPyTorch | å®å šã§ãªãã»ãã¥ãªãã£ã®åäžPython | ã®CUDA ãµããŒããç¶æ¿ããŠãããPyTorch |
ONNX | ã©ã³ã¿ã€ã ã«ããå€å | ç°ãªããã¬ãŒã ã¯ãŒã¯ã§é«ã | å€ãã®çµç¹ã«æ¯ããããå¹ åºããšã³ã·ã¹ãã | MLãã¬ãŒã ã¯ãŒã¯éã®æè»æ§ | æ°èŠäºæ¥ã®ããã®å®æçãªæŽæ° | å®å šãªå€æãšé åã®å®è·µ | æ§ã ãªããŒããŠã§ã¢ã®æé©å |
OpenVINO | Intel ããŒããŠã§ã¢ã«æé©å | Intel ãšã³ã·ã¹ãã å ã§æé« | ã³ã³ãã¥ãŒã¿ã»ããžã§ã³ã®åéã§ç¢ºåºããå®çžŸããã | Intel ããŒããŠã§ã¢ã«ããIoTãšãšããž | Intel ããŒããŠã§ã¢ã®å®æçãªã¢ããããŒã | ç¹çŽ°ãªã¢ããªã±ãŒã·ã§ã³ã®ããã®å ç¢ãªæ©èœ | Intel ããŒããŠã§ã¢ã«å¯Ÿå¿ |
TensorRT | NVIDIA GPUã§ãããã¬ãã« | NVIDIA ããŒããŠã§ã¢ã«æé© | 匷åãªãããã¯ãŒã¯NVIDIA | ãªã¢ã«ã¿ã€ã æ åã»ç»åæšè« | æ°ããGPUã®ããã®é »ç¹ãªã¢ããããŒã | ã»ãã¥ãªãã£éèŠ | NVIDIA GPUçšã«èšèš |
CoreML | ããã€ã¹äžã®Apple補ããŒããŠã§ã¢ã«æé©å | ã¢ããã«ã®ãšã³ã·ã¹ãã å°çš | ã¢ããã«ãšããããããŒã®åŒ·åãªãµããŒã | ã¢ããã«è£œåã®ãªã³ããã€ã¹ML | ã¢ããã«ã®å®æçãªã¢ããããŒã | ãã©ã€ãã·ãŒãšã»ãã¥ãªãã£ã®éèŠ | ã¢ããã«ã®ãã¥ãŒã©ã«ã»ãšã³ãžã³ãšGPU |
TF SavedModel | ãµãŒããŒç°å¢ã§ã®æ¡åŒµæ§ | TensorFlow ãšã³ã·ã¹ãã ã«ãããå¹ åºãäºææ§ | TensorFlow 人æ°ã«ãã倧ããªæ¯æ | æš¡åãã¹ã±ãŒã«ã§æäŸ | Google ãšã³ãã¥ããã£ã«ããå®æçãªæŽæ° | äŒæ¥åãã®å ç¢ãªæ©èœ | æ§ã ãªããŒããŠã§ã¢ã»ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ |
TF GraphDef | éçèšç®ã°ã©ãã®å®å®æ§ | TensorFlow ã€ã³ãã©ãšããŸãçµ±å | éçã°ã©ããæé©åããããã®ãªãœãŒã¹ | éçã°ã©ããå¿ èŠãšããã·ããªãª | TensorFlow ã³ã¢ãšäžŠè¡ããŠã¢ããããŒã | 確ç«ãããTensorFlow ã»ãã¥ãªãã£æ £è¡ | TensorFlow å éãªãã·ã§ã³ |
TF ã©ã€ã | ã¢ãã€ã«ïŒçµã¿èŸŒã¿ã«ãããã¹ããŒããšå¹çæ§ | å¹ åºãããã€ã¹ã«å¯Ÿå¿ | 匷åºãªã³ãã¥ããã£ãGoogle | ãããããªã³ããæå°éã«æããã¢ãã€ã«ã¢ããªã±ãŒã·ã§ã³ | ã¢ãã€ã«åãææ°æ©èœ | ãšã³ããŠãŒã¶ãŒã»ããã€ã¹ã®ã»ãã¥ã¢ãªç°å¢ | GPU DSPãªã© |
TF ãšããžTPU | Google's EdgeTPU ããŒããŠã§ã¢ã«æé©åãããŠããŸãã | ãšããžå°çšTPU ããã€ã¹ | Google ããµãŒãããŒãã£ã®ãªãœãŒã¹ã§æé·ãã | ãªã¢ã«ã¿ã€ã åŠçãå¿ èŠãªIoTæ©åš | æ°ããEdgeTPU ããŒããŠã§ã¢ã®æ¹å | Googleå ç¢ãªIoTã»ãã¥ãªã㣠| Google ççã®ããã®ã«ã¹ã¿ã ãã¶ã€ã³ |
TF.js | é©åºŠãªãã©ãŠã¶å ããã©ãŒãã³ã¹ | ãŠã§ãæè¡ã«é«ãé¢å¿ | Webããã³Node.jséçºè ã®ãµããŒã | ã€ã³ã¿ã©ã¯ãã£ããªãŠã§ãã¢ããªã±ãŒã·ã§ã³ | TensorFlow ããŒã ãšã³ãã¥ããã£ãžã®è²¢ç® | ãŠã§ãã»ãã©ãããã©ãŒã ã®ã»ãã¥ãªãã£ã»ã¢ãã« | WebGLããã®ä»ã®APIã§åŒ·å |
PaddlePaddle | 競äºåã䜿ãããããæ¡åŒµæ§ | çŸåºŠã®ãšã³ã·ã¹ãã ãå¹ åºãã¢ããªã±ãŒã·ã§ã³ãµããŒã | äžåœãäžå¿ã«æ¥æé· | äžåœåžå ŽãšèšèªåŠç | äžåœã®AIã¢ããªã±ãŒã·ã§ã³ã«æ³šç® | ããŒã¿ã®ãã©ã€ãã·ãŒãšã»ãã¥ãªãã£ãéèŠ | ãã€ãã¥ã®åŽåŽããããå«ã |
MNN | ã¢ãã€ã«æ©åšã®ããã®é«æ§èœã | ã¢ãã€ã«ããã³çµã¿èŸŒã¿ARMã·ã¹ãã ãšX86-64CPU | ã¢ãã€ã«ïŒçµã¿èŸŒã¿MLã³ãã¥ãã㣠| 移åã·ã¹ãã ã®å¹ç | ã¢ãã€ã«æ©åšã®é«æ§èœã¡ã³ããã³ã¹ | ãªã³ããã€ã¹ã»ã»ãã¥ãªãã£ã®å©ç¹ | ARM CPUãšGPUã®æé©å |
NCNN | ã¢ãã€ã«ARMããŒã¹ã»ããã€ã¹ã«æé©å | ã¢ãã€ã«ããã³çµã¿èŸŒã¿ARMã·ã¹ãã | ãããã ã掻çºãªã¢ãã€ã«ïŒçµã¿èŸŒã¿MLã³ãã¥ãã㣠| Android ããã³ARMã·ã¹ãã ã®å¹ç | ARMã®é«æ§èœã¡ã³ããã³ã¹ | ãªã³ããã€ã¹ã»ã»ãã¥ãªãã£ã®å©ç¹ | ARM CPUãšGPUã®æé©å |
ãã®æ¯èŒåæã§ã¯ããã€ã¬ãã«ãªæŠèŠã説æããŸããå°å ¥ã«ããã£ãŠã¯ããããžã§ã¯ãåºæã®èŠä»¶ãå¶çŽãèæ ®ããåãªãã·ã§ã³ã§å©çšå¯èœãªè©³çŽ°ãªããã¥ã¡ã³ãããªãœãŒã¹ãåç §ããããšãäžå¯æ¬ ã§ãã
ã³ãã¥ããã£ãšãµããŒã
YOLO11 ãå§ããããšãããšãã圹ã«ç«ã€ã³ãã¥ããã£ããµããŒããããã°ã倧ããªåœ±é¿ãäžããããšãã§ããŸããããã§ã¯ãåãé¢å¿ãæã€äººãã¡ãšã€ãªãããå¿ èŠãªæ¯æŽãåŸãæ¹æ³ã玹ä»ããŸãã
ããåºãã³ãã¥ããã£ãšã®é¢ãã
-
GitHubã®ãã£ã¹ã«ãã·ã§ã³GitHubã®YOLO11 ãªããžããªã«ã¯ã質åãåé¡ã®å ±åãæ¹åã®ææ¡ãã§ãã "Discussions "ã»ã¯ã·ã§ã³ããããŸãã
-
Ultralytics DiscordãµãŒããŒ: Ultralytics ã«ã¯DiscordãµãŒããŒããããä»ã®ãŠãŒã¶ãŒãéçºè ãšäº€æµããããšãã§ããŸãã
å ¬åŒææžãšãªãœãŒã¹
- Ultralytics YOLO11 ããã¥ã¡ã³ã å ¬åŒããã¥ã¡ã³ãã§ã¯ãYOLO11 ã®å æ¬çãªæŠèŠãšãã€ã³ã¹ããŒã«ã䜿çšæ¹æ³ããã©ãã«ã·ã¥ãŒãã£ã³ã°ã«é¢ããã¬ã€ããæäŸããŠããŸãã
ãããã®ãªãœãŒã¹ã¯ã課é¡ã«åãçµã¿ãYOLO11 ã³ãã¥ããã£ã®ææ°ãã¬ã³ããšãã¹ããã©ã¯ãã£ã¹ãåžžã«æŽæ°ããã®ã«åœ¹ç«ã¡ãŸãã
çµè«
ãã®ã¬ã€ãã§ã¯ãYOLO11 ã®ããŸããŸãªå°å ¥ãªãã·ã§ã³ã«ã€ããŠæ€èšããŸããããŸããéžæããéã«èæ ®ãã¹ãéèŠãªèŠçŽ ã«ã€ããŠã説æããããããã®ãªãã·ã§ã³ã«ãããæ§ã ãªç°å¢ãæ§èœèŠä»¶ã«åãããŠã¢ãã«ãã«ã¹ã¿ãã€ãºããããšãã§ããå®éã®ã¢ããªã±ãŒã·ã§ã³ã«é©ãããã®ã«ããããšãã§ããŸãã
YOLO11 ãUltralytics ã®ã³ãã¥ããã£ã貎éãªæ å ±æºã§ããããšãå¿ããªãã§ãã ãããä»ã®éçºè ãå°é家ãšã€ãªãããéåžžã®ããã¥ã¡ã³ãã«ã¯èŒã£ãŠããªããããªãŠããŒã¯ãªãã³ãã解決çãåŠã³ãŸããããç¥èãæ±ããæ°ããã¢ã€ãã¢ãæ¢æ±ããçµéšãå ±æãç¶ããŸãããã
ããããŒã»ãããã€ïŒ
ããããã質å
YOLO11 ãããŸããŸãªããŒããŠã§ã¢ã»ãã©ãããã©ãŒã ã§å©çšå¯èœãªãããã€ã¡ã³ãã»ãªãã·ã§ã³ã¯äœã§ããïŒ
Ultralytics YOLO11 ã¯ããŸããŸãªå±é圢åŒããµããŒãããŠããããããããç¹å®ã®ç°å¢ãããŒããŠã§ã¢ãã©ãããã©ãŒã åãã«èšèšãããŠããŸããäž»ãªãã©ãŒãããã¯ä»¥äžã®éãïŒ
- PyTorchç 究ããã³ãããã¿ã€ãã³ã°çšã§ãåªããPython ã
- TorchScriptPython ãå©çšã§ããªãæ¬çªç°å¢åãã
- ONNXã¯ãã¹ãã©ãããã©ãŒã ã®äºææ§ãšããŒããŠã§ã¢ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ã®ããã«ã
- OpenVINOIntel ãããŒããŠã§ã¢ã®ããã©ãŒãã³ã¹ãæé©åããã
- TensorRTNVIDIA GPUã§ã®é«éæšè«ã®ããã«ã
åãã©ãŒãããã«ã¯ç¬èªã®å©ç¹ããããŸãã詳ããã¯ããšã¯ã¹ããŒãã»ããã»ã¹ã®ããã¥ã¡ã³ããã芧ãã ããã
Intel CPU ã§YOLO11 ã¢ãã«ã®æšè«é床ãåäžãããã«ã¯ïŒ
Intel CPUã§ã®æšè«é床ãåäžãããããã«ãIntel ã®OpenVINO ããŒã«ãããã䜿çšããŠYOLO11 ã¢ãã«ãå±éããããšãã§ããŸããOpenVINO ã¯ãIntel ããŒããŠã§ã¢ãå¹ççã«æŽ»çšããããã«ã¢ãã«ãæé©åããããšã§ãããã©ãŒãã³ã¹ãå€§å¹ ã«åäžãããŸãã
- ã䜿çšããŠãYOLO11 ã¢ãã«ãOpenVINO ãã©ãŒãããã«å€æããã
model.export()
é¢æ°ã§ããã - Intel OpenVINO Export ããã¥ã¡ã³ãã®è©³çŽ°ãªã»ããã¢ããã¬ã€ãã«åŸã£ãŠãã ããã
詳ããã¯ããã°èšäºãã芧ãã ããã
YOLO11 ã¢ãã«ãã¢ãã€ã«ã»ããã€ã¹ã«å±éã§ããŸããïŒ
ã¯ããYOLO11 ã®ã¢ãã«ã¯ã ãš ã®äž¡ãã©ãããã©ãŒã çšã® Lite ( Lite ) ã䜿çšããŠã¢ãã€ã«ããã€ã¹ã«å±éã§ããŸãã TensorFlowAndroid ãšiOS ã®äž¡ãã©ãããã©ãŒã çšã® Lite (TF Lite)ãTF Liteã¯ã¢ãã€ã«ããã³çµã¿èŸŒã¿ããã€ã¹çšã«èšèšãããŠãããå¹ççãªãªã³ããã€ã¹æšè«ãæäŸããŸãã
äŸ
ã¢ãã€ã«ãžã®ã¢ãã«å±éã®è©³çŽ°ã«ã€ããŠã¯ãTF Liteã€ã³ãã°ã¬ãŒã·ã§ã³ã¬ã€ãããåç §ãã ããã
YOLO11 ã¢ãã«ã®ãããã€ã¡ã³ã圢åŒãéžæããéãã©ã®ãããªèŠçŽ ãèæ ®ãã¹ãã§ããããïŒ
YOLO11 ã®ãããã€ã¡ã³ã圢åŒãéžæããéã«ã¯ã以äžã®èŠçŽ ãèæ ®ããŠãã ããïŒ
- ããã©ãŒãã³ã¹ïŒTensorRT ã®ãããªããã€ãã®ãã©ãŒãããã¯ãNVIDIA GPU äžã§åè¶ããé床ãæäŸããããOpenVINO ã¯Intel ããŒããŠã§ã¢çšã«æé©åãããŠããã
- äºææ§ïŒONNX ã¯ãããŸããŸãªãã©ãããã©ãŒã ã§å¹ åºãäºææ§ãæäŸããã
- çµ±åã®å®¹æãïŒCoreML ãTF Lite ã®ãããªãã©ãŒãããã¯ãããããiOS ãAndroid ã®ãããªç¹å®ã®ãšã³ã·ã¹ãã çšã«èª¿æŽãããŠããã
- ã³ãã¥ããã£ãŒã®ãµããŒãïŒä»¥äžã®ãããªãã©ãŒããããããã PyTorchãTensorFlow ã®ãããªãã©ãŒãããã«ã¯ãåºç¯ãªã³ãã¥ããã£ãªãœãŒã¹ãšãµããŒããããã
æ¯èŒåæã«ã€ããŠã¯ã茞åºãã©ãŒãããã«é¢ããè³æããåç §ãã ããã
YOLO11 ã®ã¢ãã«ããŠã§ãã»ã¢ããªã±ãŒã·ã§ã³ã«å°å ¥ããã«ã¯ïŒ
ãŠã§ãã»ã¢ããªã±ãŒã·ã§ã³ã«YOLO11 ã¢ãã«ãå°å ¥ããã«ã¯ãTensorFlow.js (TF.js) ã䜿çšããããšãã§ããŸããããã¯ãæ©æ¢°åŠç¿ã¢ãã«ããã©ãŠã¶ã§çŽæ¥å®è¡ããããšãå¯èœã«ããŸãããã®ã¢ãããŒãã§ã¯ãããã¯ãšã³ãã®ã€ã³ãã©ãäžèŠã«ãªãããªã¢ã«ã¿ã€ã ã®ããã©ãŒãã³ã¹ãåŸãããã
- YOLO11 ã¢ãã«ãTF.js ãã©ãŒãããã«ãšã¯ã¹ããŒãããŸãã
- ãšã¯ã¹ããŒãããã¢ãã«ãWebã¢ããªã±ãŒã·ã§ã³ã«çµ±åããŸãã
ã¹ããããã€ã¹ãããã®æé ã«ã€ããŠã¯ãTensorFlow.jsã®çµ±åã«é¢ããã¬ã€ããåç §ããŠãã ããã