From c7983813144f550832cedfbc8fe26ef0b0a7fc5d Mon Sep 17 00:00:00 2001 From: Sadik Armagan Date: Thu, 20 Feb 2020 16:51:15 +0000 Subject: IVGCVSW-4432 Update Readme for 20.02 Signed-off-by: Sadik Armagan Change-Id: I416b39b0adac1410f854d3ec5b855044bd85e1cc --- src/armnnDeserializer/DeserializerSupport.md | 3 +++ src/armnnSerializer/SerializerSupport.md | 1 + src/armnnTfLiteParser/TensorFlowLiteSupport.md | 6 ++++++ src/armnnTfParser/TensorFlowSupport.md | 6 +++++- src/dynamic/README.md | 2 +- 5 files changed, 16 insertions(+), 2 deletions(-) diff --git a/src/armnnDeserializer/DeserializerSupport.md b/src/armnnDeserializer/DeserializerSupport.md index fcadaccb79..491cd1de42 100644 --- a/src/armnnDeserializer/DeserializerSupport.md +++ b/src/armnnDeserializer/DeserializerSupport.md @@ -21,6 +21,7 @@ The Arm NN SDK Deserialize parser currently supports the following layers: * Dequantize * DetectionPostProcess * Division +* ElementwiseUnary * Floor * FullyConnected * Gather @@ -43,6 +44,8 @@ The Arm NN SDK Deserialize parser currently supports the following layers: * Quantize * QuantizedLstm * Reshape +* Resize +* ResizeBilinear * Rsqrt * Slice * Softmax diff --git a/src/armnnSerializer/SerializerSupport.md b/src/armnnSerializer/SerializerSupport.md index 2f77a8e778..79b551f03a 100644 --- a/src/armnnSerializer/SerializerSupport.md +++ b/src/armnnSerializer/SerializerSupport.md @@ -44,6 +44,7 @@ The Arm NN SDK Serializer currently supports the following layers: * QuantizedLstm * Reshape * Resize +* ResizeBilinear * Slice * Softmax * SpaceToBatchNd diff --git a/src/armnnTfLiteParser/TensorFlowLiteSupport.md b/src/armnnTfLiteParser/TensorFlowLiteSupport.md index 145ca9f747..22023f1671 100644 --- a/src/armnnTfLiteParser/TensorFlowLiteSupport.md +++ b/src/armnnTfLiteParser/TensorFlowLiteSupport.md @@ -18,6 +18,8 @@ The Arm NN SDK TensorFlow Lite parser currently supports the following operators * DEPTHWISE_CONV_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE +* DEQUANTIZE + * FULLY_CONNECTED, Supported Fused Activation: RELU , RELU6 , TANH, NONE * LOGISTIC @@ -38,6 +40,8 @@ The Arm NN SDK TensorFlow Lite parser currently supports the following operators * PAD +* QUANTIZE + * RELU * RELU6 @@ -46,6 +50,8 @@ The Arm NN SDK TensorFlow Lite parser currently supports the following operators * RESIZE_BILINEAR +* RESIZE_NEAREST_NEIGHBOR + * SLICE * SOFTMAX diff --git a/src/armnnTfParser/TensorFlowSupport.md b/src/armnnTfParser/TensorFlowSupport.md index 343d7a5773..68c7209284 100644 --- a/src/armnnTfParser/TensorFlowSupport.md +++ b/src/armnnTfParser/TensorFlowSupport.md @@ -163,10 +163,14 @@ Arm NN supports split along the channel dimension for data formats NHWC and NCHW The parser does not support all forms of broadcasting [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of scalars and 1D tensors. See the TensorFlow [subtract documentation](https://www.tensorflow.org/api_docs/python/tf/math/subtract) for more information. -**stack** +**pack/stack** See the TensorFlow [stack documentation](https://www.tensorflow.org/api_docs/python/tf/stack) for more information. +**strided_slice** + +See the TensorFlow [strided_slice documentation](https://www.tensorflow.org/api_docs/python/tf/strided_slice) for more information. + ## Tested networks Arm tests these operators with the following TensorFlow fp32 neural networks: diff --git a/src/dynamic/README.md b/src/dynamic/README.md index d0e4d778d2..36a238a7ba 100644 --- a/src/dynamic/README.md +++ b/src/dynamic/README.md @@ -32,7 +32,7 @@ cd build cmake -DBOOST_ROOT=${BOOST_PATH} \ -DBoost_SYSTEM_LIBRARY=${BOOST_PATH}/lib/libboost_system.a \ -DBoost_FILESYSTEM_LIBRARY=${BOOST_PATH}/lib/libboost_filesystem.a \ - -DARMNN_PATH=${ARMNN_PAH}/libarmnn.so .. + -DARMNN_PATH=${ARMNN_PATH}/libarmnn.so .. ``` Then run the build -- cgit v1.2.1