Gitiles
Code Review Sign In
review.mlplatform.org / ml / armnn / 8eae955f665f371b0a2c7c1a06e8ba442afa2298 / . / docs / 01_03_delegate.dox
blob: 9063f05658b45f3e0201d9c832f3c9444d221b69 [file] [log] [blame]
Jan Eilers31a7c892021-01-29 14:18:13 +0000[diff] [blame]1/// Copyright (c) 2021 ARM Limited and Contributors. All rights reserved.
2///
3/// SPDX-License-Identifier: MIT
4///
5
6namespace armnn
7{
8/**
9@page delegate TfLite Delegate
10@tableofcontents
11
12
13@section delegateintro About the delegate
14'armnnDelegate' is a library for accelerating certain TensorFlow Lite (TfLite) operators on Arm hardware. It can be
15integrated in TfLite using its delegation mechanism. TfLite will then delegate the execution of operators supported by
16Arm NN to Arm NN.
17
18The main difference to our @ref S6_tf_lite_parser is the amount of operators you can run with it. If none of the active
19backends support an operation in your model you won't be able to execute it with our parser. In contrast to that, TfLite
20only delegates operations to the armnnDelegate if it does support them and otherwise executes them itself. In other
21words, every TfLite model can be executed and every operation in your model that we can accelerate will be accelerated.
22That is the reason why the armnnDelegate is our recommended way to accelerate TfLite models.
23
24If you need help building the armnnDelegate, please take a look at our [build guide](delegate/BuildGuideNative.md).
25An example how to setup TfLite to integrate the armnnDelegate can be found in this
26guide: [Integrate the delegate into python](delegate/IntegrateDelegateIntoPython.md)
27
28
29@section delegatesupport Supported Operators
30This reference guide provides a list of TensorFlow Lite operators the Arm NN SDK currently supports.
31
32@subsection delegatefullysupported Fully supported
33
34The Arm NN SDK TensorFlow Lite delegate currently supports the following operators:
35
36- ABS
37
38- ADD
39
40- ARGMAX
41
42- ARGMIN
43
44- AVERAGE_POOL_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE
45
Matthew Sloyana35b40b2021-02-05 17:22:28 +0000[diff] [blame]46- BATCH_TO_SPACE_ND
47
Jan Eilers31a7c892021-01-29 14:18:13 +0000[diff] [blame]48- CONCATENATION, Supported Fused Activation: RELU , RELU6 , TANH, NONE
49
50- CONV_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE
51
52- DEPTH_TO_SPACE
53
54- DEPTHWISE_CONV_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE
55
56- DEQUANTIZE
57
58- DIV
59
60- EQUAL
61
62- ELU
63
64- EXP
65
66- FULLY_CONNECTED, Supported Fused Activation: RELU , RELU6 , TANH, NONE
67
Sadik Armagan788e2c62021-02-10 16:26:44 +0000[diff] [blame]68- FLOOR
69
Jan Eilers31a7c892021-01-29 14:18:13 +0000[diff] [blame]70- GATHER
71
72- GREATER
73
74- GREATER_OR_EQUAL
75
76- HARD_SWISH
77
78- LESS
79
80- LESS_OR_EQUAL
81
82- LOCAL_RESPONSE_NORMALIZATION
83
84- LOGICAL_AND
85-
86- LOGICAL_NOT
87-
88- LOGICAL_OR
89
90- LOGISTIC
91
92- LOG_SOFTMAX
93
94- L2_NORMALIZATION
95
96- L2_POOL_2D
97
98- MAXIMUM
99
100- MAX_POOL_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE
101
102- MEAN
103
104- MINIMUM
105
106- MUL
107
108- NEG
109
110- NOT_EQUAL
111
112- PAD
113
114- QUANTIZE
115
116- RESHAPE
117
118- RESIZE_BILINEAR
119
120- RESIZE_NEAREST_NEIGHBOR
121
122- RELU
123
124- RELU6
125
126- RSQRT
127
128- SOFTMAX
129
Matthew Sloyana35b40b2021-02-05 17:22:28 +0000[diff] [blame]130- SPACE_TO_BATCH_ND
131
Jan Eilers31a7c892021-01-29 14:18:13 +0000[diff] [blame]132- SPACE_TO_DEPTH
133
134- SPLIT
135
136- SPLIT_V
137
138- SQRT
139
140- SUB
141
142- TANH
143
144- TRANSPOSE
145
146- TRANSPOSE_CONV
147
148More machine learning operators will be supported in future releases.
149**/
150}