OAID/TensorFlow-HRT
Heterogeneous Run Time version of TensorFlow. Added heterogeneous capabilities to the TensorFlow, 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 TensorFlow architecture which users deploy their applications seamlessly.
This project helps developers accelerate deep learning model execution on Arm-based embedded systems. It takes your existing TensorFlow deep learning applications and uses heterogeneous computing to deliver faster performance on devices like the Rockchip RK3399. The ideal end-users are embedded systems engineers or AI hardware developers working with Arm platforms.
No commits in the last 6 months.
Use this if you need to deploy and run TensorFlow deep learning models efficiently on Arm-based embedded hardware and require debugging and profiling tools for performance tuning.
Not ideal if you are working with non-Arm architectures or are not focused on embedded system deployment, as current performance gains may be limited for certain TensorFlow operations.
Stars
36
Forks
18
Language
C++
License
Apache-2.0
Category
Last pushed
Feb 12, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OAID/TensorFlow-HRT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
iree-org/iree
A retargetable MLIR-based machine learning compiler and runtime toolkit.
brucefan1983/GPUMD
Graphics Processing Units Molecular Dynamics
uxlfoundation/oneDAL
oneAPI Data Analytics Library (oneDAL)
rapidsai/cuml
cuML - RAPIDS Machine Learning Library
NVIDIA/cutlass
CUDA Templates and Python DSLs for High-Performance Linear Algebra