1 /// Copyright (c) 2021 ARM Limited and Contributors. All rights reserved.
3 /// SPDX-License-Identifier: MIT
9 @page serializer Serializer
12 The `armnnSerializer` is a library for serializing an Arm NN network to a stream.
14 @section serializersupport Supported Layers
16 This reference guide provides a list of layers which can be serialized by the Arm NN SDK.
18 @subsection serializersupportflully Fully supported
20 The Arm NN SDK Serializer currently supports the following layers:
32 - DepthwiseConvolution2d
34 - DetectionPostProcess
42 - InstanceNormalization
76 - TransposeConvolution2d
78 More machine learning layers will be supported in future releases.
80 @subsection serializersupportdeprecated Deprecated layers
82 Some 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:
84 - Abs will deserialize as ElementwiseUnary
85 - Equal will deserialize as Comparison
86 - Greater will deserialize as Comparison
87 - Merger will deserialize as Concat
88 - ResizeBilinear will deserialize as Resize
89 - Rsqrt will deserialize as ElementwiseUnary
92 @page deserializer Deserializer
95 The `armnnDeserializer` is a library for loading neural networks defined by Arm NN FlatBuffers files
96 into the Arm NN runtime.
98 @section deserializersupport Supported Layers
100 This reference guide provides a list of layers which can be deserialized by the Arm NN SDK.
102 @subsection deserializersupportfully Fully supported
104 The Arm NN SDK Deserialize parser currently supports the following layers:
117 - DepthwiseConvolution2d
119 - DetectionPostProcess
127 - InstanceNormalization
162 - TransposeConvolution2d
164 More machine learning layers will be supported in future releases.
166 @subsection deserializersupportdeprecated Deprecated layers
168 Some 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:
170 - Equal will deserialize as Comparison
171 - Merger will deserialize as Concat
172 - Greater will deserialize as Comparison
173 - ResizeBilinear will deserialize as Resize