From 0ec008761ab26110dcb108d544be4040a14fd403 Mon Sep 17 00:00:00 2001 From: John Mcloughlin Date: Mon, 15 May 2023 17:03:49 +0100 Subject: IVGCVSW-7400 POW IVGCVSW-7278 SQUARED_DIFFERENCE. * Added 2 new operators as ElementWiseBinary ops * Ref End to End and unit tests * Serialize and Deserialize tests * Delegate and Opaque Delegate tests * TfLite Parser tests Signed-off-by: John Mcloughlin Change-Id: I537158127f602f0c41ca0402aa31655cd3bd4281 --- docs/02_operator_list.dox | 46 ++++++++++++++++++++++++++++++++++++++++++++++ docs/05_01_parsers.dox | 2 ++ docs/05_03_delegate.dox | 4 ++++ 3 files changed, 52 insertions(+) (limited to 'docs') diff --git a/docs/02_operator_list.dox b/docs/02_operator_list.dox index 53e37e2b4e..16b0f0b14c 100644 --- a/docs/02_operator_list.dox +++ b/docs/02_operator_list.dox @@ -1163,6 +1163,52 @@ where N = batches, C = channels, H = height, W = width FLOAT16 FLOAT32 + + ElementwiseBinaryLayer + Layer to perform Power and Square Difference operations. + + + CpuRef + + + + +
+
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+ + CpuAcc + + + + +
+
FLOAT16 +
FLOAT32 +
+ + GpuAcc + + + + +
+
FLOAT16 +
FLOAT32 +
ElementwiseUnaryLayer Layer to perform Rsqrt - Exp - Neg - Log - Abs - Sin - Sqrt operations. diff --git a/docs/05_01_parsers.dox b/docs/05_01_parsers.dox index e8d4797227..08d569d065 100644 --- a/docs/05_01_parsers.dox +++ b/docs/05_01_parsers.dox @@ -162,6 +162,7 @@ The Arm NN SDK TensorFlow Lite parser currently supports the following operators - PACK - PAD - PADV2 +- POW - PRELU - QUANTIZE - RELU @@ -183,6 +184,7 @@ The Arm NN SDK TensorFlow Lite parser currently supports the following operators - SPLIT_V - SQUEEZE - SQRT +- SQUARE_DIFFERENCE - STRIDED_SLICE - SUB - SUM diff --git a/docs/05_03_delegate.dox b/docs/05_03_delegate.dox index b804268e90..49d6af31e6 100644 --- a/docs/05_03_delegate.dox +++ b/docs/05_03_delegate.dox @@ -141,6 +141,8 @@ The Arm NN SDK TensorFlow Lite delegate currently supports the following operato - PADV2 +- POW + - PRELU - QUANTIZE @@ -183,6 +185,8 @@ The Arm NN SDK TensorFlow Lite delegate currently supports the following operato - SQRT +- SQUARE_DIFFERENCE + - SQUEEZE - SLICE -- cgit v1.2.1