From ce3e84a8d449cbf31cee57e30f0eef6a96c0ce94 Mon Sep 17 00:00:00 2001 From: telsoa01 Date: Fri, 31 Aug 2018 09:31:35 +0100 Subject: Release 18.08 --- NnapiSupport.txt | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'NnapiSupport.txt') diff --git a/NnapiSupport.txt b/NnapiSupport.txt index 8973d901..de2e4071 100644 --- a/NnapiSupport.txt +++ b/NnapiSupport.txt @@ -1,6 +1,7 @@ ------ 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 interface. +android.hardware.neuralnetworks@1.1 models available in Android P can be executed if they return true from the utility method compliantWithV1_0(model). For more information on the Android Neural Networks API, see https://developer.android.com/ndk/guides/neuralnetworks/index.html @@ -31,21 +32,35 @@ RESHAPE (FLOAT32,QUANT8_ASYMM) RESIZE_BILINEAR (FLOAT32) SOFTMAX (FLOAT32,QUANT8_ASYMM) TANH (FLOAT32) +LSTM (FLOAT32) * Depthwise convolution only supports a value of 1 for the depth multiplier. In addition, the QUANT8_ASYMM version only supports 3x3 kernels. --- Unsupported operators --- -The following AndroidNN operations are currently not supported. +The following AndroidNN 1.0 operations are currently not supported. DEPTH_TO_SPACE DEQUANTIZE EMBEDDING_LOOKUP HASHTABLE_LOOKUP LSH_PROJECTION -LSTM RNN SPACE_TO_DEPTH SVDF 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. + +The following AndroidNN 1.1 operations are currently not supported. + +BATCH_TO_SPACE_ND +DIV +MEAN +PAD +SPACE_TO_BATCH_ND +SQUEEZE +STRIDED_SLICE +SUB +TRANSPOSE + +Where any of these operations are present the model will return false from the compliantWithV1_0(model) and the driver will not currently be utilised. -- cgit v1.2.1