From 7bfd38a721360183f3392f9ab35db18a0dd7fef8 Mon Sep 17 00:00:00 2001 From: Nikhil Raj Date: Fri, 19 Aug 2022 15:23:36 +0100 Subject: Update Doxygen for 22.08 Release Signed-off-by: Nikhil Raj Change-Id: I4789fe868e0492839be1482e5cee3642ed90d756 --- 22.08/serializer.xhtml | 207 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 207 insertions(+) create mode 100644 22.08/serializer.xhtml (limited to '22.08/serializer.xhtml') diff --git a/22.08/serializer.xhtml b/22.08/serializer.xhtml new file mode 100644 index 0000000000..2631788ab0 --- /dev/null +++ b/22.08/serializer.xhtml @@ -0,0 +1,207 @@ + + + + + + + + + + + + + +ArmNN: Serializer + + + + + + + + + + + + + + + + +
+
+ + + + ArmNN + + + +
+
+  22.08 +
+
+
+ + + + + + + +
+
+ +
+
+
+ +
+ +
+
+ + +
+ +
+ +
+
+
Serializer
+
+
+

Table of Contents

+ +
+

The armnnSerializer is a library for serializing an Arm NN network to a stream.

+

+Supported Layers

+

This reference guide provides a list of layers which can be serialized by the Arm NN SDK.

+

+Fully supported

+

The Arm NN SDK Serializer currently supports the following layers:

+
    +
  • Activation
    • +
  • Addition
    • +
  • ArgMinMax
    • +
  • BatchToSpaceNd
    • +
  • BatchNormalization
    • +
  • Cast
    • +
  • ChannelShuffle
    • +
  • Comparison
    • +
  • Concat
    • +
  • Constant
    • +
  • Convolution2d
    • +
  • Convolution3d
    • +
  • DepthToSpace
    • +
  • DepthwiseConvolution2d
    • +
  • Dequantize
    • +
  • DetectionPostProcess
    • +
  • Division
    • +
  • ElementwiseUnary
    • +
  • Fill
    • +
  • Floor
    • +
  • FullyConnected
    • +
  • Gather
    • +
  • GatherNd
    • +
  • Input
    • +
  • InstanceNormalization
    • +
  • L2Normalization
    • +
  • Logical
    • +
  • LogSoftmax
    • +
  • Lstm
    • +
  • Maximum
    • +
  • Mean
    • +
  • Merge
    • +
  • Minimum
    • +
  • Multiplication
    • +
  • Normalization
    • +
  • Output
    • +
  • Pad (Constant, Symmetric, Reflect)
    • +
  • Permute
    • +
  • Pooling2d
    • +
  • Pooling3d
    • +
  • Prelu
    • +
  • QLstm
    • +
  • Quantize
    • +
  • QuantizedLstm
    • +
  • Rank
    • +
  • Reduce
    • +
  • Reshape
    • +
  • Resize
    • +
  • Shape
    • +
  • Slice
    • +
  • Softmax
    • +
  • SpaceToBatchNd
    • +
  • SpaceToDepth
    • +
  • Splitter
    • +
  • Stack
    • +
  • StandIn
    • +
  • StridedSlice
    • +
  • Subtraction
    • +
  • Switch
    • +
  • Transpose
    • +
  • TransposeConvolution2d
    • +
  • UnidirectionalSequenceLstm
    • +
+

More machine learning layers will be supported in future releases.

+

+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
    +
    +
    +
    +
    • +
+
+
+ + + + -- cgit v1.2.1