mirror of https://github.com/Qortal/Brooklyn
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
178 lines
2.9 KiB
178 lines
2.9 KiB
/// Copyright (c) 2021 ARM Limited and Contributors. All rights reserved. |
|
/// |
|
/// SPDX-License-Identifier: MIT |
|
/// |
|
|
|
namespace armnn |
|
{ |
|
/** |
|
@page delegate TfLite Delegate |
|
@tableofcontents |
|
|
|
|
|
@section delegateintro About the delegate |
|
'armnnDelegate' is a library for accelerating certain TensorFlow Lite (TfLite) operators on Arm hardware. It can be |
|
integrated in TfLite using its delegation mechanism. TfLite will then delegate the execution of operators supported by |
|
Arm NN to Arm NN. |
|
|
|
The main difference to our @ref S6_tf_lite_parser is the amount of operators you can run with it. If none of the active |
|
backends support an operation in your model you won't be able to execute it with our parser. In contrast to that, TfLite |
|
only delegates operations to the armnnDelegate if it does support them and otherwise executes them itself. In other |
|
words, every TfLite model can be executed and every operation in your model that we can accelerate will be accelerated. |
|
That is the reason why the armnnDelegate is our recommended way to accelerate TfLite models. |
|
|
|
If you need help building the armnnDelegate, please take a look at our [build guide](delegate/BuildGuideNative.md). |
|
An example how to setup TfLite to integrate the armnnDelegate can be found in this |
|
guide: [Integrate the delegate into python](delegate/IntegrateDelegateIntoPython.md) |
|
|
|
|
|
@section delegatesupport Supported Operators |
|
This reference guide provides a list of TensorFlow Lite operators the Arm NN SDK currently supports. |
|
|
|
@subsection delegatefullysupported Fully supported |
|
|
|
The Arm NN SDK TensorFlow Lite delegate currently supports the following operators: |
|
|
|
- ABS |
|
|
|
- ADD |
|
|
|
- ARGMAX |
|
|
|
- ARGMIN |
|
|
|
- AVERAGE_POOL_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE |
|
|
|
- BATCH_TO_SPACE_ND |
|
|
|
- CAST |
|
|
|
- CONCATENATION, Supported Fused Activation: RELU , RELU6 , TANH, NONE |
|
|
|
- CONV_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE |
|
|
|
- CONV_3D, Supported Fused Activation: RELU , RELU6 , TANH, NONE |
|
|
|
- DEPTH_TO_SPACE |
|
|
|
- DEPTHWISE_CONV_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE |
|
|
|
- DEQUANTIZE |
|
|
|
- DIV |
|
|
|
- EQUAL |
|
|
|
- ELU |
|
|
|
- EXP |
|
|
|
- FULLY_CONNECTED, Supported Fused Activation: RELU , RELU6 , TANH, NONE |
|
|
|
- FLOOR |
|
|
|
- GATHER |
|
|
|
- GREATER |
|
|
|
- GREATER_OR_EQUAL |
|
|
|
- HARD_SWISH |
|
|
|
- LESS |
|
|
|
- LESS_OR_EQUAL |
|
|
|
- LOCAL_RESPONSE_NORMALIZATION |
|
|
|
- LOGICAL_AND |
|
|
|
- LOGICAL_NOT |
|
|
|
- LOGICAL_OR |
|
|
|
- LOGISTIC |
|
|
|
- LOG_SOFTMAX |
|
|
|
- LSTM |
|
|
|
- L2_NORMALIZATION |
|
|
|
- L2_POOL_2D |
|
|
|
- MAXIMUM |
|
|
|
- MAX_POOL_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE |
|
|
|
- MEAN |
|
|
|
- MINIMUM |
|
|
|
- MIRROR_PAD |
|
|
|
- MUL |
|
|
|
- NEG |
|
|
|
- NOT_EQUAL |
|
|
|
- PACK |
|
|
|
- PAD |
|
|
|
- PRELU |
|
|
|
- QUANTIZE |
|
|
|
- RANK |
|
|
|
- REDUCE_MAX |
|
|
|
- REDUCE_MIN |
|
|
|
- RESHAPE |
|
|
|
- RESIZE_BILINEAR |
|
|
|
- RESIZE_NEAREST_NEIGHBOR |
|
|
|
- RELU |
|
|
|
- RELU6 |
|
|
|
- RSQRT |
|
|
|
- SHAPE |
|
|
|
- SOFTMAX |
|
|
|
- SPACE_TO_BATCH_ND |
|
|
|
- SPACE_TO_DEPTH |
|
|
|
- SPLIT |
|
|
|
- SPLIT_V |
|
|
|
- SQRT |
|
|
|
- STRIDED_SLICE |
|
|
|
- SUB |
|
|
|
- SUM |
|
|
|
- TANH |
|
|
|
- TRANSPOSE |
|
|
|
- TRANSPOSE_CONV |
|
|
|
- UNIDIRECTIONAL_SEQUENCE_LSTM |
|
|
|
- UNPACK |
|
|
|
More machine learning operators will be supported in future releases. |
|
**/ |
|
} |