saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-14 18:12:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/docs/reference/execution-providers/RKNPU-ExecutionProvider.md
Scott McKay 9e8d795344
Update ORT Mobile documentation (#7874) 
* Update ORT Mobile documentation for both the pre-built package and custom build usage
Add info on pre-built package and CoreML EP
Refer to operator kernels and contrib ops documentation in github so we can point to the version specific content
Tweak some aspects like not specifying nav_order in places (items sort alphabetically by default)

* merge previous unmerged ios doc updates

* Address PR comments

* Minor tweaks

* Address PR comments

Co-authored-by: Guoyu Wang <wanggy@outlook.com>
2021-06-01 21:21:41 -07:00

1.8 KiB
Raw Blame History

title parent grand_parent
RKNPU Execution Providers Reference

RKNPU Execution Provider

PREVIEW

RKNPU DDK is an advanced interface to access Rockchip NPU. The RKNPU Execution Provider enables deep learning inference on Rockchip NPU via RKNPU DDK.

Contents

{: .no_toc }

  • TOC placeholder {:toc}

Build

For build instructions, please see the BUILD page.

Usage

C/C++

To use RKNPU as an execution provider for inferencing, please register it as below.

Ort::Env env = Ort::Env{ORT_LOGGING_LEVEL_ERROR, "Default"};
Ort::SessionOptions sf;
Ort::ThrowOnError(OrtSessionOptionsAppendExecutionProvider_RKNPU(sf));
Ort::Session session(env, model_path, sf);

The C API details are here.

Support Coverage

Supported Platform

{: .no_toc }

  • RK1808 Linux

Note: RK3399Pro platform is not supported.

Supported Operators

{: .no_toc }

The table below shows the ONNX Ops supported using the RKNPU Execution Provider and the mapping between ONNX Ops and RKNPU Ops.

ONNX Ops RKNPU Ops
Add ADD
Mul MULTIPLY
Conv CONV2D
QLinearConv CONV2D
Gemm FULLCONNECT
Softmax SOFTMAX
AveragePool POOL
GlobalAveragePool POOL
MaxPool POOL
GlobalMaxPool POOL
LeakyRelu LEAKY_RELU
Concat CONCAT
BatchNormalization BATCH_NORM
Reshape RESHAPE
Flatten RESHAPE
Squeeze RESHAPE
Unsqueeze RESHAPE
Transpose PERMUTE
Relu RELU
Sub SUBTRACT
Clip(0~6) RELU6
DequantizeLinear DATACONVERT
Clip CLIP

Supported Models

{: .no_toc }

The following models from the ONNX model zoo are supported using the RKNPU Execution Provider

Image Classification

  • squeezenet
  • mobilenetv2-1.0
  • resnet50v1
  • resnet50v2
  • inception_v2

Object Detection

  • ssd
  • yolov3