commit 613b49cdd8f4e40460711a4d84ed42f980477a17
author David Monahan <david.monahan@arm.com> Thu Jun 27 11:37:47 2019 +0100
committer Narumol Prangnawarat <narumol.prangnawarat@arm.com> Tue Jul 30 10:56:23 2019 +0100
tree 4ea6a6bdd1f32227cd26a63c532a7d21d19c6dc9
parent 5a476a88c3295168f5480b5861f59255b29d8433

IVGCVSW-3166 Add support for TransposeConv2D to 1.2 HalPolicy

Signed-off-by: David Monahan <david.monahan@arm.com>
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I7b855efaddb18e8f184f4b85196b3b95b69bca6e

NnapiSupport.txt

diff --git a/NnapiSupport.txt b/NnapiSupport.txt
index 47c5149..4a49430 100644
--- a/NnapiSupport.txt
+++ b/NnapiSupport.txt
@@ -57,6 +57,7 @@
 QUANTIZE                     (FLOAT32,QUANT8_ASYMM)
 RESIZE_NEAREST_NEIGHBOR      (FLOAT32,QUANT8_ASYMM)
 SOFTMAX                      (FLOAT32,QUANT8_ASYMM)
+TRANSPOSE_CONV_2D            (FLOAT32,QUANT8_ASYMM)
 
 --- Unsupported operators ---
 
@@ -74,7 +75,6 @@
 CONCATENATION
 LSTM
 QUANTIZED_16BIT_LSTM
-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.