The armnnDeserializer is a library for loading neural networks defined by Arm NN FlatBuffers files into the Arm NN runtime.
Supported Layers
This reference guide provides a list of layers which can be deserialized by the Arm NN SDK.
Fully supported
The Arm NN SDK Deserialize parser currently supports the following layers:
- Abs
- Activation
- Addition
- ArgMinMax
- BatchToSpaceNd
- BatchNormalization
- Cast
- ChannelShuffle
- Concat
- Comparison
- Constant
- Convolution2d
- 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
- Permute
- Pooling2d
- Pooling3d
- Prelu
- Quantize
- QLstm
- QuantizedLstm
- Rank
- Reduce
- Reshape
- Resize
- ResizeBilinear
- 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:
- Equal will deserialize as Comparison
- Merger will deserialize as Concat
- Greater will deserialize as Comparison
- ResizeBilinear will deserialize as Resize
1.8.13 