Gitiles
Code Review Sign In
review.mlplatform.org / ml / armnn / f0a6dec75832604d5ab18242dc216852821a8279 / . / docs / 01_02_deserializer_serializer.dox
blob: 6884b93dd14ba4681810a7004775fcafdc77f551 [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
27- Comparison
28- Concat
29- Constant
30- Convolution2d
31- DepthToSpace
32- DepthwiseConvolution2d
33- Dequantize
34- DetectionPostProcess
35- Division
36- ElementwiseUnary
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]37- Fill
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]38- Floor
39- FullyConnected
40- Gather
41- Input
42- InstanceNormalization
43- L2Normalization
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]44- Logical
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]45- LogSoftmax
46- Lstm
47- Maximum
48- Mean
49- Merge
50- Minimum
51- Multiplication
52- Normalization
53- Output
54- Pad
55- Permute
56- Pooling2d
57- Prelu
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]58- QLstm
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]59- Quantize
60- QuantizedLstm
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]61- Rank
Jan Eilers1121c6b2021-02-19 09:38:03 +0000[diff] [blame]62- Reduce
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]63- Reshape
64- Resize
65- Slice
66- Softmax
67- SpaceToBatchNd
68- SpaceToDepth
69- Splitter
70- Stack
71- StandIn
72- StridedSlice
73- Subtraction
74- Switch
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]75- Transpose
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]76- TransposeConvolution2d
77
78More machine learning layers will be supported in future releases.
79
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]80@subsection serializersupportdeprecated Deprecated layers
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]81
82Some 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:
83
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]84- Abs will deserialize as ElementwiseUnary
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]85- Equal will deserialize as Comparison
86- Greater will deserialize as Comparison
87- Merger will deserialize as Concat
88- ResizeBilinear will deserialize as Resize
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]89- Rsqrt will deserialize as ElementwiseUnary
90<br/><br/><br/><br/>
91
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]92@page deserializer Deserializer
93@tableofcontents
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]94
95The `armnnDeserializer` is a library for loading neural networks defined by Arm NN FlatBuffers files
96into the Arm NN runtime.
97
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]98@section deserializersupport Supported Layers
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]99
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]100This 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]101
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]102@subsection deserializersupportfully Fully supported
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]103
104The Arm NN SDK Deserialize parser currently supports the following layers:
105
106- Abs
107- Activation
108- Addition
109- ArgMinMax
110- BatchToSpaceNd
111- BatchNormalization
112- Concat
113- Comparison
114- Constant
115- Convolution2d
116- DepthToSpace
117- DepthwiseConvolution2d
118- Dequantize
119- DetectionPostProcess
120- Division
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]121- ElementwiseUnary
122- Fill
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]123- Floor
124- FullyConnected
125- Gather
126- Input
127- InstanceNormalization
128- L2Normalization
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]129- Logical
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]130- LogSoftmax
131- Lstm
132- Maximum
133- Mean
134- Merge
135- Minimum
136- Multiplication
137- Normalization
138- Output
139- Pad
140- Permute
141- Pooling2d
142- Prelu
143- Quantize
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]144- QLstm
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]145- QuantizedLstm
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]146- Rank
Jan Eilers1121c6b2021-02-19 09:38:03 +0000[diff] [blame]147- Reduce
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]148- Reshape
James Ward590f3f72020-12-02 10:20:48 +0000[diff] [blame]149- Resize
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]150- ResizeBilinear
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]151- Slice
152- Softmax
153- SpaceToBatchNd
154- SpaceToDepth
155- Splitter
156- Stack
157- StandIn
158- StridedSlice
159- Subtraction
160- Switch
Jan Eilers1121c6b2021-02-19 09:38:03 +0000[diff] [blame]161- Transpose
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]162- TransposeConvolution2d
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]163
164More machine learning layers will be supported in future releases.
165
Jan Eilers1ed388f2021-01-28 14:45:09 +0000[diff] [blame]166@subsection deserializersupportdeprecated Deprecated layers
Ryan OSheaf3a43232020-02-12 16:15:27 +0000[diff] [blame]167
168Some 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:
169
170- Equal will deserialize as Comparison
171- Merger will deserialize as Concat
172- Greater will deserialize as Comparison
173- ResizeBilinear will deserialize as Resize
174
175**/
176}