OAID/MXNet-HRT

Heterogeneous Run Time version of MXNet. Added heterogeneous capabilities to the MXNet, uses heterogeneous computing infrastructure framework to speed up Deep Learning on Arm-based heterogeneous embedded platform. It also retains all the features of the original MXNet architecture which users deploy their applications seamlessly.

45
/ 100
Emerging

This project helps embedded systems developers speed up deep learning applications on Arm-based hardware platforms. It takes your existing MXNet-based deep learning models and optimizes their performance, especially on devices like the Rockchip RK3399. The result is faster execution of your AI models on embedded systems.

No commits in the last 6 months.

Use this if you are developing deep learning applications for Arm-based embedded platforms and need to accelerate the inference speed of your MXNet models.

Not ideal if you are working with non-Arm hardware, or if your primary deep learning framework is not MXNet.

embedded-systems deep-learning-deployment edge-ai system-optimization AI-hardware-acceleration
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

72

Forks

30

Language

C++

License

Apache-2.0

Last pushed

Feb 11, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OAID/MXNet-HRT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.