diff options
| author | saoste01 <saoirse.stewart@arm.com> | 2018-10-18 17:49:56 +0100 |
|---|---|---|
| committer | Matthew Bentham <matthew.bentham@arm.com> | 2018-10-22 17:25:39 +0100 |
| commit | fe463150228156c29a415f45d2172a43df6ce6c3 (patch) | |
| tree | 39496d6ab97ea631613ee5c0dbf33f7c3a6aafb1 /NnapiSupport.txt | |
| parent | 5e0ed9fb1e86a45617c65376c4756b8317798e5e (diff) | |
| download | android-nn-driver-fe463150228156c29a415f45d2172a43df6ce6c3.tar.gz | |
IVGCVSW-2020: Add converter method for TRANSPOSE to the V1.1 section of HalPolicy
* Updating SQUEEZE with comments from TRANSPOSE
Change-Id: Iec48c5d583fecc5e72082d7de0fc8b1becfd84d7
Diffstat (limited to 'NnapiSupport.txt')
| -rw-r--r-- | NnapiSupport.txt | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/NnapiSupport.txt b/NnapiSupport.txt index a47edf5f..8d56edd9 100644 --- a/NnapiSupport.txt +++ b/NnapiSupport.txt @@ -33,6 +33,7 @@ RESIZE_BILINEAR (FLOAT32) 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 @@ PAD 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. |