Here are some numbers illustrating the performance I have seen for the Nvidia Jetson Nano so far.<\/p>\n
Deep learning\u00a0<\/strong><\/p>\n Training this\u00a0PyTorch Image Classifier<\/a>\u00a0with the flower data set, took just under 10 hours for the full 30 epochs.\u00a0 Not at all bad, and really quite nice if you consider the average power consumption of less than 8 watts.<\/p>\n Numbers from two different workstations have been included for comparison, of course, these spent more than 500 watts on average.<\/p>\n Nvidia Jetson Nano: Dell Precision T7500 Workstation: Dell Precision 7920 Rack Workstation: Network performance\u00a0<\/strong><\/p>\n The Jetson Nano clocked in at 857 Mbps as measured with iperf to a Dell Precision T7500 workstation, interconnected with a Netgear ProSAFE GS108T switch. I believe the workstation would do close to 950 Mbps when connected to a proper Cisco Catalyst like the 2960-X.<\/p>\n As one might expect, compared to a Raspberry Pi the Jetson Nano did absolutely beautifully.<\/p>\n Nvidia Jetson Nano: 857 Mbps Here are some numbers illustrating the performance I have seen for the Nvidia Jetson Nano so far. Deep learning\u00a0 Training this\u00a0PyTorch Image Classifier\u00a0with the flower data set, took just under 10 hours for the full 30 epochs.\u00a0 Not at all … Continue reading
\n– GPU (Nvidia Maxwell): < 10 hours<\/p>\n
\n– CPU (Dual Intel Xeon E5620): < 30 hours
\n– GPU (Nvidia GeForce GTX 1060): < 40 minutes<\/p>\n
\n– CPU (Dual Intel Xeon Silver 4112): <\u00a0 9 hours
\n– GPU (Nvidia Quadro RTX 5000): < 17 minutes<\/span><\/p>\n
\nRaspberry Pi 3 B+: 292 Mbps
\nBroadcom NetXtreme BCM5761: 878 Mbps (between two T7500 workstations)<\/p>\n","protected":false},"excerpt":{"rendered":"