diff options
| author | Ferran Balaguer <ferran.balaguer@arm.com> | 2018-11-15 14:48:05 +0000 |
|---|---|---|
| committer | Ferran Balaguer <ferran.balaguer@arm.com> | 2018-11-15 14:48:05 +0000 |
| commit | d04c04375e42621b3d7abaff0a827105d7312517 (patch) | |
| tree | 027778209cbaffe95add40853b071820a4d5ebc1 /NnapiSupport.txt | |
| parent | 2cd99b9767df70e0f8f802e497a5c719650c676f (diff) | |
| download | android-nn-driver-d04c04375e42621b3d7abaff0a827105d7312517.tar.gz | |
IVGCVSW-2080 Fix documentation in NnapiSupport.txt
Change-Id: Id369a2a70863fabaa60ee11849b5449dd95e25a7
Diffstat (limited to 'NnapiSupport.txt')
| -rw-r--r-- | NnapiSupport.txt | 17 |
1 files changed, 6 insertions, 11 deletions
diff --git a/NnapiSupport.txt b/NnapiSupport.txt index ea3fa8f2..0f62da7e 100644 --- a/NnapiSupport.txt +++ b/NnapiSupport.txt @@ -18,14 +18,18 @@ BATCH_TO_SPACE_ND (FLOAT32,QUANT8_ASYMM) CONCATENATION (FLOAT32) CONV_2D (FLOAT32,QUANT8_ASYMM) DEPTHWISE_CONV_2D* (FLOAT32,QUANT8_ASYMM) +DIV (FLOAT32,QUANT8_ASYMM) FLOOR (FLOAT32) FULLY_CONNECTED (FLOAT32,QUANT8_ASYMM) L2_NORMALIZATION (FLOAT32) L2_POOL_2D (FLOAT32) LOCAL_RESPONSE_NORMALIZATION (FLOAT32) LOGISTIC (FLOAT32,QUANT8_ASYMM) +LSTM (FLOAT32) MAX_POOL_2D (FLOAT32,QUANT8_ASYMM) +MEAN (FLOAT32,QUANT8_ASYMM) MUL (FLOAT32,QUANT8_ASYMM) +PAD (FLOAT32,QUANT8_ASYMM) RELU (FLOAT32,QUANT8_ASYMM) RELU1 (FLOAT32,QUANT8_ASYMM) RELU6 (FLOAT32,QUANT8_ASYMM) @@ -34,9 +38,10 @@ RESIZE_BILINEAR (FLOAT32) SOFTMAX (FLOAT32,QUANT8_ASYMM) SPACE_TO_BATCH_ND (FLOAT32,QUANT8_ASYMM) SQUEEZE (FLOAT32,QUANT8_ASYMM) +STRIDED_SLICE (FLOAT32,QUANT8_ASYMM) +SUB (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. @@ -54,13 +59,3 @@ 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. - -DIV -MEAN -PAD -STRIDED_SLICE -SUB - -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. |