aboutsummaryrefslogtreecommitdiff
path: root/docs/01_02_deserializer_serializer.dox
diff options
context:
space:
mode:
authorJan Eilers <jan.eilers@arm.com>2021-01-29 14:18:13 +0000
committerJan Eilers <jan.eilers@arm.com>2021-02-03 09:11:51 +0000
commit31a7c890207f80afc866f706d797267d78d05a0d (patch)
tree8b133170fbdf0d87a0a8a5b72c6eaf73fcbb2391 /docs/01_02_deserializer_serializer.dox
parent74a3cf5755b801cf258177e8e55b4cda64a0c351 (diff)
downloadarmnn-31a7c890207f80afc866f706d797267d78d05a0d.tar.gz
IVGCVSW-5605 Doxygen: Add the TfLite Delegate to Doxygen docu
* Moves TensorFlowLiteDelegateSupport.md to doxygen * Renames a few .dox files to represent the structure of the documentation * Adds sections for build and use guides * Integrates markdown guides for the delegate into doxygen Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I68b7a29239be88c0617da9bdfce5323ebf26f5bc
Diffstat (limited to 'docs/01_02_deserializer_serializer.dox')
-rw-r--r--docs/01_02_deserializer_serializer.dox174
1 files changed, 174 insertions, 0 deletions
diff --git a/docs/01_02_deserializer_serializer.dox b/docs/01_02_deserializer_serializer.dox
new file mode 100644
index 0000000000..047cb5dc8d
--- /dev/null
+++ b/docs/01_02_deserializer_serializer.dox
@@ -0,0 +1,174 @@
+/// Copyright (c) 2021 ARM Limited and Contributors. All rights reserved.
+///
+/// SPDX-License-Identifier: MIT
+///
+
+namespace armnn
+{
+/**
+@page serializer Serializer
+@tableofcontents
+
+The `armnnSerializer` is a library for serializing an Arm NN network to a stream.
+
+@section serializersupport Supported Layers
+
+This reference guide provides a list of layers which can be serialized by the Arm NN SDK.
+
+@subsection serializersupportflully Fully supported
+
+The Arm NN SDK Serializer currently supports the following layers:
+
+- Activation
+- Addition
+- ArgMinMax
+- BatchToSpaceNd
+- BatchNormalization
+- Comparison
+- Concat
+- Constant
+- Convolution2d
+- DepthToSpace
+- DepthwiseConvolution2d
+- Dequantize
+- DetectionPostProcess
+- Division
+- ElementwiseUnary
+- Fill
+- Floor
+- FullyConnected
+- Gather
+- Input
+- InstanceNormalization
+- L2Normalization
+- Logical
+- LogSoftmax
+- Lstm
+- Maximum
+- Mean
+- Merge
+- Minimum
+- Multiplication
+- Normalization
+- Output
+- Pad
+- Permute
+- Pooling2d
+- Prelu
+- QLstm
+- Quantize
+- QuantizedLstm
+- Rank
+- Reshape
+- Resize
+- Slice
+- Softmax
+- SpaceToBatchNd
+- SpaceToDepth
+- Splitter
+- Stack
+- StandIn
+- StridedSlice
+- Subtraction
+- Switch
+- Transpose
+- TransposeConvolution2d
+
+More machine learning layers will be supported in future releases.
+
+@subsection serializersupportdeprecated Deprecated layers
+
+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:
+
+- Abs will deserialize as ElementwiseUnary
+- Equal will deserialize as Comparison
+- Greater will deserialize as Comparison
+- Merger will deserialize as Concat
+- ResizeBilinear will deserialize as Resize
+- Rsqrt will deserialize as ElementwiseUnary
+<br/><br/><br/><br/>
+
+@page deserializer Deserializer
+@tableofcontents
+
+The `armnnDeserializer` is a library for loading neural networks defined by Arm NN FlatBuffers files
+into the Arm NN runtime.
+
+@section deserializersupport Supported Layers
+
+This reference guide provides a list of layers which can be deserialized by the Arm NN SDK.
+
+@subsection deserializersupportfully Fully supported
+
+The Arm NN SDK Deserialize parser currently supports the following layers:
+
+- Abs
+- Activation
+- Addition
+- ArgMinMax
+- BatchToSpaceNd
+- BatchNormalization
+- Concat
+- Comparison
+- Constant
+- Convolution2d
+- DepthToSpace
+- DepthwiseConvolution2d
+- Dequantize
+- DetectionPostProcess
+- Division
+- ElementwiseUnary
+- Fill
+- Floor
+- FullyConnected
+- Gather
+- Input
+- InstanceNormalization
+- L2Normalization
+- Logical
+- LogSoftmax
+- Lstm
+- Maximum
+- Mean
+- Merge
+- Minimum
+- Multiplication
+- Normalization
+- Output
+- Pad
+- Permute
+- Pooling2d
+- Prelu
+- Quantize
+- QLstm
+- QuantizedLstm
+- Rank
+- Reshape
+- Resize
+- ResizeBilinear
+- Rsqrt
+- Slice
+- Softmax
+- SpaceToBatchNd
+- SpaceToDepth
+- Splitter
+- Stack
+- StandIn
+- StridedSlice
+- Subtraction
+- Switch
+- TransposeConvolution2d
+
+More machine learning layers will be supported in future releases.
+
+@subsection deserializersupportdeprecated Deprecated layers
+
+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:
+
+- Equal will deserialize as Comparison
+- Merger will deserialize as Concat
+- Greater will deserialize as Comparison
+- ResizeBilinear will deserialize as Resize
+
+**/
+} \ No newline at end of file