OAID/Caffe-HRT
Heterogeneous Run Time version of Caffe. Added heterogeneous capabilities to the Caffe, 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 Caffe architecture which users deploy their applications seamlessly.
This project helps deep learning engineers accelerate their Caffe-based deep learning models on embedded Arm-based platforms. It takes existing Caffe deep learning models and optimizes their execution by leveraging heterogeneous computing, providing faster performance for vision and machine learning tasks. Developers deploying AI applications on embedded systems would use this to improve model speed.
269 stars. No commits in the last 6 months.
Use this if you are a deep learning developer working with Caffe models on Arm-based embedded systems and need to improve their execution speed.
Not ideal if you are not using Caffe, developing on a non-Arm platform, or are not focused on embedded deep learning performance.
Stars
269
Forks
96
Language
C++
License
—
Category
Last pushed
Oct 16, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OAID/Caffe-HRT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
onnx/onnx
Open standard for machine learning interoperability
PINTO0309/onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The...
NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This...
onnx/onnxmltools
ONNXMLTools enables conversion of models to ONNX