IVGCVSW-2020: Add converter method for TRANSPOSE to the V1.1 section of HalPolicy
* Updating SQUEEZE with comments from TRANSPOSE
Change-Id: Iec48c5d583fecc5e72082d7de0fc8b1becfd84d7
diff --git a/NnapiSupport.txt b/NnapiSupport.txt
index a47edf5..8d56edd 100644
--- a/NnapiSupport.txt
+++ b/NnapiSupport.txt
@@ -33,6 +33,7 @@
SOFTMAX (FLOAT32,QUANT8_ASYMM)
SQUEEZE (FLOAT32,QUANT8_ASYMM)
TANH (FLOAT32)
+TRANSPOSE (FLOAT32,QUANT8_ASYMM)
LSTM (FLOAT32)
* Depthwise convolution only supports a value of 1 for the depth multiplier. In addition, the QUANT8_ASYMM version only supports 3x3 kernels.
@@ -61,6 +62,5 @@
SPACE_TO_BATCH_ND
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.