dusty-nv / jetson-inference

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
https://developer.nvidia.com/embedded/twodaystoademo
MIT License
7.86k stars 2.98k forks source link

Can someone tell me which Jetson Device is being referred to in this repo when they say "Xavier" #928

Closed sisaha9 closed 3 years ago

sisaha9 commented 3 years ago

https://github.com/dusty-nv/jetson-inference#semantic-segmentation

I know Jetson Nano but which Xavier is being referred to here? Xavier NX or AGX Xavier?

dusty-nv commented 3 years ago

That was with Jetson AGX Xavier

From: sisaha9 notifications@github.com Sent: Thursday, February 18, 2021 1:30 PM To: dusty-nv/jetson-inference jetson-inference@noreply.github.com Cc: Subscribed subscribed@noreply.github.com Subject: [dusty-nv/jetson-inference] Can someone tell me which Jeetson Device is being referred to in this repo when they say "Xavier" (#928)

https://github.com/dusty-nv/jetson-inference#semantic-segmentation

I know Jetson Nano but which Xavier is being referred to here? Xavier NX or AGX Xavier?

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHubhttps://github.com/dusty-nv/jetson-inference/issues/928, or unsubscribehttps://github.com/notifications/unsubscribe-auth/ADVEGK5DQXQHAIKOFD4QRZ3S7VMD3ANCNFSM4X2ZUEMA.

sisaha9 commented 3 years ago

Which semantic segmentation model would you recommend for real time inference in Xavier NX?

sisaha9 commented 3 years ago

I have 720x1280 images but I will scale down if need be since fast real time inference is important for my application (self driving car)

dusty-nv commented 3 years ago

They should all still be realtime on NX. If your input is 1280x720, try fcn-resnet18-cityscapes-1024x512 or fcn-resnet18-cityscapes-512x256

sisaha9 commented 3 years ago

Got it. Thanks!