wateret/one_private

On-device Neural Engine

nnfw

A high-performance, on-device neural network inference framework

Goal

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.

Project Documents

• Roadmap
• SW Requirement Specification
• SW High Level Design

Getting started

• For the contribution, please refer to our contribution guide.
• You can also find how-to documents HERE.

Maintainers

• Sung-Jae Lee <[email protected]>
• Chunseok Lee <[email protected]>

Committers

• Hyeongseok Oh <[email protected]>
• Hanjoung Lee <[email protected]>
• Sharan Allur <[email protected]>

Feature Request (NEW)

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_REQUEST label 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!

nncc

Re-targetable neural network (NN) model compilation framework

Goals

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.

Maintainers

• Sung-Jae Lee <[email protected]>
• Jonghyun Park <[email protected]>

Committers

• Saehie Park <[email protected]>
• Hyeongseok Oh <[email protected]>
• Efimov Alexander <[email protected]>

How to Contact

• Please post questions, issues, or suggestions into Issues.

---

Notice

22/07/2019

Congratulations! On July 22nd, 2019, nnfw repo and nncc repo are finally integrated into single one. Now all activities related to the development of nnas(Neural Network Acceleration Solution) will proceed in this integrated nnfw repo. The old nncc repo will only be maintained for follow up on remaining issues and for preserving development history. The following notice will remain in place until the update of documents in integrated repo is complete.

02/05/2019

We are currently working on nncc as a sibling project. In our plan, the two projects will soon be integrated into one, and focusing on their roles as front-end(nncc) and back-end(nnfw), respectively. It will accompany the physical combination of the github repo. You can find the latest roadmap of the integrated project here.