Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

'binaries/jetson' is faster than 'binaries/jetson_tftrt' on Jetson Xavier AGX #128

Open
DoubangoTelecom opened this issue Jan 18, 2021 · 0 comments
Labels
help wanted Extra attention is needed to be investigated We have to investigate and will come back later

Comments

@DoubangoTelecom
Copy link
Owner

Jetson Xavier AGX has an 8 cores CPU @2.Ghz which is fast enough to handle OCR task. The parallel mode is faster when you perform the detection and classification (VCR, VMMR, VBSR, LPCI...) on GPU and LPR/OCR on CPU. You'll be using the CPU and GPU in parallel.

Rule of thumb: Try the benchmark application on your device with both 'binaries/jetson' and 'binaries/jetson_tftrt' and take the fastest.

@DoubangoTelecom DoubangoTelecom added to be investigated We have to investigate and will come back later help wanted Extra attention is needed labels Feb 3, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
help wanted Extra attention is needed to be investigated We have to investigate and will come back later
Projects
None yet
Development

No branches or pull requests

1 participant