MobileViT-XS has a third fewer parameters than MobileNetV2 and 1.5 points more accuracy. On an iPhone 12 it is about 8x slower.

Parameters said faster. MACs said 2.3x. The phone said 7.9x.

Runtime engineers: has fused attention closed that gap on Jetson?

#EdgeAI #Jetson

Banana Pi BPI-SM10 (K3-CoM260) delivers up to 60 TOPS of general-purpose AI compute,with 8-32G RAM
docs.banana-pi.org/en/BPI-SM10/...
#NVIDIA #Jetson #Nano #BananaPi #RaspberryPi #AI #Robots #Edge #Spacemit #K3

Banana Pi BPI-CM5 Pro is a computing module powered by the Rockchip RK3576, 6 TOPS computing power NPU,8-32G RAM and 8-128G eMMC,are you want o do Edge AI project or replace Raspberry Pi CM4？
docs.banana-pi.org/en/BPI-CM5_P...
#NVIDIA #Jetson #Nano #BananaPi #RaspberryPi #AI #Robots #Edge

Banana Pi BPI-AIM7 with Rockchip RK3588, 6 TOPS computing power NPU,8-32G RAM and 8-128G eMMC,what Edge AI project are you want to do.
docs.banana-pi.org/en/BPI-AIM7/...
#NVIDIA #Jetson #Nano #BananaPi #RaspberryPi #AI #Robot

The first NAS run cost 22,400 GPU-days. Weight sharing cut that about 50,000x. The search strategy got the credit; cheaper evaluation did the work.

Edge AI teams: do you search against your own device's latency, or ship a backbone searched for someone else's?

#EdgeAI #Jetson

Pour bien comprendre :
ESP 32 : 10/20 €
Arduino Q : 50/60 €
Rasberry Pi 5 : 200/250 €
Jetson Nano : 500/600 €

#esp #arduino #raspeberry #jetson #jestsonnano

www.youtube.com/shorts/iY0gN...

MobileNetV2 has 47% fewer MACs than MobileNetV1. On the @nvidiabot.bsky.social Jetson Orin Nano it runs about 7% faster.

Every efficiency trick relocates the bottleneck: to the 1x1 then to memory.

Kernel and compiler engineers: has fusion closed the depthwise gap on your hardware?

#EdgeAI #Jetson

Think AI is just for your laptop? Think again! NVIDIA's powerful Jetson robotics platform, fueled by Firefly Aerospace, is officially heading

#NVIDIA #Readies #Jetson #Robotics #Platforms

We made it easy to install Isaac ROS! The new `isaac-forge` repository contains many upstream NVIDIA Isaac ROS packages to make them installable with Pixi. You can test it today on your #NIVIDA #Jetson!

No docker needed!

github.com/wolfv/isaac...

MobileNetV2 on the Jetson Orin Nano: 12.5 ms end to end. Convolution is 3.8 ms of it.

Time only the kernels and you are 3x optimistic. Skip the synchronize and you are 100x optimistic.

What fraction of your reported latency is actually the model?

#EdgeAI #Jetson