Gitiles
Code Review Sign In
review.mlplatform.org / ml / armnn / 3ae3f978cf9ce3174609b7152af87acb410b0fe0 / . / docs / 01_02_deserializer_serializer.dox
blob: 811af1cfb56b3ec92010e9889a12ef71d111b1e3 [file] [log] [blame]
Jan Eilers31a7c892021-01-29 14:18:13 +0000[diff] [blame]1/// Copyright (c) 2021 ARM Limited and Contributors. All rights reserved.
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]2///
3/// SPDX-License-Identifier: MIT
4///
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]5
6namespace armnn
7{
8/**
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]9@page serializer Serializer
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]10@tableofcontents
11
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]12The `armnnSerializer` is a library for serializing an Arm NN network to a stream.
13
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]14@section serializersupport Supported Layers
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]15
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]16This reference guide provides a list of layers which can be serialized by the Arm NN SDK.
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]17
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]18@subsection serializersupportflully Fully supported
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]19
20The Arm NN SDK Serializer currently supports the following layers:
21
22- Activation
23- Addition
24- ArgMinMax
25- BatchToSpaceNd
26- BatchNormalization
mathad01b392e982021-04-07 12:07:30 +0100[diff] [blame]27- Cast
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]28- Comparison
29- Concat
30- Constant
31- Convolution2d
32- DepthToSpace
33- DepthwiseConvolution2d
34- Dequantize
35- DetectionPostProcess
36- Division
37- ElementwiseUnary
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]38- Fill
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]39- Floor
40- FullyConnected
41- Gather
42- Input
43- InstanceNormalization
44- L2Normalization
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]45- Logical
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]46- LogSoftmax
47- Lstm
48- Maximum
49- Mean
50- Merge
51- Minimum
52- Multiplication
53- Normalization
54- Output
55- Pad
56- Permute
57- Pooling2d
58- Prelu
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]59- QLstm
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]60- Quantize
61- QuantizedLstm
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]62- Rank
Jan Eilers1121c6b2021-02-19 09:38:03 +0000[diff] [blame]63- Reduce
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]64- Reshape
65- Resize
Keith Davis3ae3f972021-05-21 16:33:48 +0100[diff] [blame^]66- Shape
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]67- Slice
68- Softmax
69- SpaceToBatchNd
70- SpaceToDepth
71- Splitter
72- Stack
73- StandIn
74- StridedSlice
75- Subtraction
76- Switch
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]77- Transpose
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]78- TransposeConvolution2d
79
80More machine learning layers will be supported in future releases.
81
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]82@subsection serializersupportdeprecated Deprecated layers
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]83
84Some layers have been deprecated and replaced by others layers. In order to maintain backward compatibility, serializations of these deprecated layers will deserialize to the layers that have replaced them, as follows:
85
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]86- Abs will deserialize as ElementwiseUnary
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]87- Equal will deserialize as Comparison
88- Greater will deserialize as Comparison
89- Merger will deserialize as Concat
90- ResizeBilinear will deserialize as Resize
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]91- Rsqrt will deserialize as ElementwiseUnary
92<br/><br/><br/><br/>
93
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]94@page deserializer Deserializer
95@tableofcontents
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]96
97The `armnnDeserializer` is a library for loading neural networks defined by Arm NN FlatBuffers files
98into the Arm NN runtime.
99
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]100@section deserializersupport Supported Layers
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]101
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]102This reference guide provides a list of layers which can be deserialized by the Arm NN SDK.
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]103
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]104@subsection deserializersupportfully Fully supported
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]105
106The Arm NN SDK Deserialize parser currently supports the following layers:
107
108- Abs
109- Activation
110- Addition
111- ArgMinMax
112- BatchToSpaceNd
113- BatchNormalization
mathad01b392e982021-04-07 12:07:30 +0100[diff] [blame]114- Cast
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]115- Concat
116- Comparison
117- Constant
118- Convolution2d
119- DepthToSpace
120- DepthwiseConvolution2d
121- Dequantize
122- DetectionPostProcess
123- Division
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]124- ElementwiseUnary
125- Fill
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]126- Floor
127- FullyConnected
128- Gather
129- Input
130- InstanceNormalization
131- L2Normalization
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]132- Logical
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]133- LogSoftmax
134- Lstm
135- Maximum
136- Mean
137- Merge
138- Minimum
139- Multiplication
140- Normalization
141- Output
142- Pad
143- Permute
144- Pooling2d
145- Prelu
146- Quantize
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]147- QLstm
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]148- QuantizedLstm
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]149- Rank
Jan Eilers1121c6b2021-02-19 09:38:03 +0000[diff] [blame]150- Reduce
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]151- Reshape
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]152- Resize
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]153- ResizeBilinear
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]154- Slice
155- Softmax
156- SpaceToBatchNd
157- SpaceToDepth
158- Splitter
159- Stack
160- StandIn
161- StridedSlice
162- Subtraction
163- Switch
Jan Eilers1121c6b2021-02-19 09:38:03 +0000[diff] [blame]164- Transpose
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]165- TransposeConvolution2d
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]166
167More machine learning layers will be supported in future releases.
168
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]169@subsection deserializersupportdeprecated Deprecated layers
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]170
171Some layers have been deprecated and replaced by others layers. In order to maintain backward compatibility, serializations of these deprecated layers will deserialize to the layers that have replaced them, as follows:
172
173- Equal will deserialize as Comparison
174- Merger will deserialize as Concat
175- Greater will deserialize as Comparison
176- ResizeBilinear will deserialize as Resize
177
178**/
179}