aboutsummaryrefslogtreecommitdiff
path: root/NnapiSupport.txt
diff options
context:
space:
mode:
Diffstat (limited to 'NnapiSupport.txt')
-rw-r--r--NnapiSupport.txt2
1 files changed, 1 insertions, 1 deletions
diff --git a/NnapiSupport.txt b/NnapiSupport.txt
index d5e077bf..e3d7c692 100644
--- a/NnapiSupport.txt
+++ b/NnapiSupport.txt
@@ -54,6 +54,7 @@ PAD_V2 (FLOAT32, FLOAT16, QUANT8_ASYMM)
PRELU (FLOAT32, QUANT8_ASYMM)
QUANTIZE (FLOAT32 (input only), QUANT8_ASYMM (output only))
QUANTIZED_16BIT_LSTM (QUANT8_ASYMM)
+QUANTIZED_LSTM (QUANT8_ASYMM)
RELU (FLOAT32, QUANT8_ASYMM)
RELU1 (FLOAT32, QUANT8_ASYMM)
RELU6 (FLOAT32, QUANT8_ASYMM)
@@ -74,7 +75,6 @@ TRANSPOSE_CONV_2D (FLOAT32, QUANT8_ASYMM)
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.
-
NOTE: By convention, only those tensor types have been listed above, which are fully supported across all
ArmNN backends. FLOAT16 input tensors are partially supported on most HAL 1.2 operators on the GpuAcc and
CpuRef backends, however not on CpuAcc.