A high-performance, on-device neural network inference framework
This project nnfw aims at providing a high-performance, on-device neural network (NN) inference framework that performs inference of a given NN model on processors, such as CPU, GPU, or NPU, in the target platform, such as the Linux kernel based OS including Tizen.
- For the contribution, please refer to our contribution guide.
- You can also find how-to documents HERE.
- Sung-Jae Lee <[email protected]>
- Chunseok Lee <[email protected]>
- Hyeongseok Oh <[email protected]>
- Hanjoung Lee <[email protected]>
- Sharan Allur <[email protected]>
You can suggest development of nnfw's features that are not yet available.
The functions requested so far can be checked in the popular feature request list.
-
If the feature you want is on the list, 👍 to the body of the issue. The feature with the most 👍 is placed at the top of the list. When adding new features, we will prioritize them with this reference. Of course, it is good to add an additional comment which describes your request in detail.
-
For features not listed, create a new issue. Sooner or later, the maintainer will tag the
FEATURE_REQUESTlabel and appear on the list.
We expect one of the most frequent feature requests would be the operator kernel implementation. It is good to make a request, but it is better if you contribute by yourself. See the following guide, How to Implement Operator Kernel, for help.
We are looking forward to your participation. Thank you in advance!
Re-targetable neural network (NN) model compilation framework
nncc, which stands for neural network compiler collection, aims to provide a general framework for compiling a given NN model to an artifact that runs on various target devices such as CPU, GPU, or NPU.
- Sung-Jae Lee <[email protected]>
- Jonghyun Park <[email protected]>
- Saehie Park <[email protected]>
- Hyeongseok Oh <[email protected]>
- Efimov Alexander <[email protected]>
- Please post questions, issues, or suggestions into Issues.