From b23732bcd6cb51bc7a4da369b1654bfa02a70c00 Mon Sep 17 00:00:00 2001 From: Aron Virginas-Tar Date: Mon, 17 Jun 2019 15:48:45 +0100 Subject: Update documentation with dilated CONV_2D and DEPTHWISE_CONV_2D Signed-off-by: Aron Virginas-Tar Change-Id: I1d210ca2a6bed2ee35a7ed5c2877197f83a0f340 --- NnapiSupport.txt | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) (limited to 'NnapiSupport.txt') diff --git a/NnapiSupport.txt b/NnapiSupport.txt index bdd1843f..b4b2cc45 100644 --- a/NnapiSupport.txt +++ b/NnapiSupport.txt @@ -1,8 +1,8 @@ ------ ArmNN for Android NNAPI supported operations ------ This release of ArmNN for Android supports use as a driver for the Android Neural Networks API. It implements the -android.hardware.neuralnetworks@1.0, android.hardware.neuralnetworks@1.1 HAL and android.hardware.neuralnetworks@1.2 HAL -interfaces. +android.hardware.neuralnetworks@1.0, android.hardware.neuralnetworks@1.1 and android.hardware.neuralnetworks@1.2 +HAL interfaces. For more information on the Android Neural Networks API, see https://developer.android.com/ndk/guides/neuralnetworks/index.html @@ -10,7 +10,7 @@ For integration and usage documentation, please see README.md. --- Support for Android Neural Networks HAL operations --- -The following AndroidNN operations are currently supported. +The following AndroidNN HAL 1.0 and 1.1 operations are currently supported: AndroidNN operator Tensor type supported ADD (FLOAT32,QUANT8_ASYMM) @@ -45,10 +45,14 @@ SUB (FLOAT32,QUANT8_ASYMM) TANH (FLOAT32,QUANT8_ASYMM) TRANSPOSE (FLOAT32,QUANT8_ASYMM) +The following AndroidNN HAL 1.2 operations are currently supported: + +CONV_2D (FLOAT32,QUANT8_ASYMM) +DEPTHWISE_CONV_2D (FLOAT32,QUANT8_ASYMM) --- Unsupported operators --- -The following AndroidNN 1.0 operations are currently not supported. +The following AndroidNN HAL 1.0 operations are currently not supported: DEPTH_TO_SPACE EMBEDDING_LOOKUP @@ -58,5 +62,18 @@ RNN SPACE_TO_DEPTH SVDF +The following AndroidNN HAL 1.2 operations are currently not supported: + +CONCATENATION +LSTM +MINIMUM +MAXIMUM +PAD_V2 +QUANTIZE +QUANTIZED_16BIT_LSTM +PRELU +RESIZE_NEAREST_NEIGHBOR +TRANSPOSE_CONV_2D + Where operations are not supported by the ArmNN Android NN Driver, the driver indicates this to the framework appropriately and the framework implements those operations using a CPU implementation. -- cgit v1.2.1