From 48f9ac0ba3a08cec47857fcb78138cebbaf6088e Mon Sep 17 00:00:00 2001 From: Narumol Prangnawarat Date: Thu, 21 May 2020 14:27:48 +0100 Subject: IVGCVSW-4792 Update armnn readme and support files * Add Transpose to SerializerSupport.md * Remove ResizeBilinear as it is deprecated layer * Add EXP and SPLIT_V to TensorFlowLiteSupport.md * Add transpose to TensorFlowSupport.md Signed-off-by: Narumol Prangnawarat Change-Id: I05b0411b61c1b74b27b4669e81fa8ce521bb4190 --- src/armnnCaffeParser/CaffeSupport.md | 2 +- src/armnnCaffeParser/README.md | 2 +- src/armnnSerializer/SerializerSupport.md | 6 +++--- src/armnnTfLiteParser/TensorFlowLiteSupport.md | 4 ++++ src/armnnTfParser/TensorFlowSupport.md | 4 ++++ 5 files changed, 13 insertions(+), 5 deletions(-) diff --git a/src/armnnCaffeParser/CaffeSupport.md b/src/armnnCaffeParser/CaffeSupport.md index 9e4f1fa993..5d998937de 100644 --- a/src/armnnCaffeParser/CaffeSupport.md +++ b/src/armnnCaffeParser/CaffeSupport.md @@ -1,4 +1,4 @@ -#Caffe layers supported by the Arm NN SDK +# Caffe layers supported by the Arm NN SDK This reference guide provides a list of Caffe layers the Arm NN SDK currently supports. Although some other neural networks might work, Arm tests the Arm NN SDK with Caffe implementations of the following neural networks: diff --git a/src/armnnCaffeParser/README.md b/src/armnnCaffeParser/README.md index 89f0a3f586..63e856dfdc 100644 --- a/src/armnnCaffeParser/README.md +++ b/src/armnnCaffeParser/README.md @@ -1,4 +1,4 @@ -#Arm NN Caffe parser +# Arm NN Caffe parser `armnnCaffeParser` is a library for loading neural networks defined in Caffe protobuf files into the Arm NN runtime. diff --git a/src/armnnSerializer/SerializerSupport.md b/src/armnnSerializer/SerializerSupport.md index 8ba164c91e..f8d86551ae 100644 --- a/src/armnnSerializer/SerializerSupport.md +++ b/src/armnnSerializer/SerializerSupport.md @@ -45,7 +45,6 @@ The Arm NN SDK Serializer currently supports the following layers: * QuantizedLstm * Reshape * Resize -* ResizeBilinear * Slice * Softmax * SpaceToBatchNd @@ -56,6 +55,7 @@ The Arm NN SDK Serializer currently supports the following layers: * StridedSlice * Subtraction * Switch +* Transpose * TransposeConvolution2d More machine learning layers will be supported in future releases. @@ -64,10 +64,10 @@ More machine learning layers will be supported in future releases. 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 -* Merger will deserialize as Concat * Greater will deserialize as Comparison +* Merger will deserialize as Concat * ResizeBilinear will deserialize as Resize -* Abs will deserialize as ElementwiseUnary * Rsqrt will deserialize as ElementwiseUnary diff --git a/src/armnnTfLiteParser/TensorFlowLiteSupport.md b/src/armnnTfLiteParser/TensorFlowLiteSupport.md index 22023f1671..88db0f07b2 100644 --- a/src/armnnTfLiteParser/TensorFlowLiteSupport.md +++ b/src/armnnTfLiteParser/TensorFlowLiteSupport.md @@ -20,6 +20,8 @@ The Arm NN SDK TensorFlow Lite parser currently supports the following operators * DEQUANTIZE +* EXP + * FULLY_CONNECTED, Supported Fused Activation: RELU , RELU6 , TANH, NONE * LOGISTIC @@ -60,6 +62,8 @@ The Arm NN SDK TensorFlow Lite parser currently supports the following operators * SPLIT +* SPLIT_V + * SQUEEZE * STRIDED_SLICE diff --git a/src/armnnTfParser/TensorFlowSupport.md b/src/armnnTfParser/TensorFlowSupport.md index 68c7209284..65839e2e57 100644 --- a/src/armnnTfParser/TensorFlowSupport.md +++ b/src/armnnTfParser/TensorFlowSupport.md @@ -78,6 +78,10 @@ See the TensorFlow [squeeze documentation](https://www.tensorflow.org/api_docs/p See the TensorFlow [tanh documentation](https://www.tensorflow.org/api_docs/python/tf/tanh) for more information. +**transpose** + +See the TensorFlow [transpose documentation](https://www.tensorflow.org/api_docs/python/tf/transpose) for more information. + ## Partially supported **add** -- cgit v1.2.1