diff options
Diffstat (limited to 'src')
| -rw-r--r-- | src/armnnDeserializer/DeserializerSupport.md | 75 | ||||
| -rw-r--r-- | src/armnnDeserializer/README.md | 3 | ||||
| -rw-r--r-- | src/armnnSerializer/README.md | 3 | ||||
| -rw-r--r-- | src/armnnSerializer/SerializerSupport.md | 76 |
4 files changed, 4 insertions, 153 deletions
diff --git a/src/armnnDeserializer/DeserializerSupport.md b/src/armnnDeserializer/DeserializerSupport.md deleted file mode 100644 index 2ff3a24503..0000000000 --- a/src/armnnDeserializer/DeserializerSupport.md +++ /dev/null @@ -1,75 +0,0 @@ -# The layers that ArmNN SDK Deserializer currently supports. - -This reference guide provides a list of layers which can be deserialized currently by the Arm NN SDK. - -## 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. - -## 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 diff --git a/src/armnnDeserializer/README.md b/src/armnnDeserializer/README.md index 28d6a37388..fa76a6da45 100644 --- a/src/armnnDeserializer/README.md +++ b/src/armnnDeserializer/README.md @@ -4,4 +4,5 @@ The `armnnDeserializer` is a library for loading neural networks defined by Arm into the Arm NN runtime. For more information about the layers that are supported, and the networks that have been tested, -see [DeserializerSupport.md](./DeserializerSupport.md)
\ No newline at end of file +take a look into our doxygen documentation which can be found in the [wiki section](https://github.com/ARM-software/armnn/wiki/Documentation) +of our github repository.
\ No newline at end of file diff --git a/src/armnnSerializer/README.md b/src/armnnSerializer/README.md index 0656c8bb79..79ab2e2c17 100644 --- a/src/armnnSerializer/README.md +++ b/src/armnnSerializer/README.md @@ -3,4 +3,5 @@ The `armnnSerializer` is a library for serializing an Arm NN network to a stream. For more information about the layers that are supported, and the networks that have been tested, -see [SerializerSupport.md](./SerializerSupport.md). +take a look into our doxygen documentation which can be found in the [wiki section](https://github.com/ARM-software/armnn/wiki/Documentation) +of our github repository.
\ No newline at end of file diff --git a/src/armnnSerializer/SerializerSupport.md b/src/armnnSerializer/SerializerSupport.md deleted file mode 100644 index 67dc5d1596..0000000000 --- a/src/armnnSerializer/SerializerSupport.md +++ /dev/null @@ -1,76 +0,0 @@ -# The layers that ArmNN SDK Serializer currently supports. - -This reference guide provides a list of layers which can be serialized currently by the Arm NN SDK. - -## 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. - -## 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 - |