diff options
author | Ellen Norris-Thompson <ellen.norris-thompson@arm.com> | 2019-07-24 17:39:19 +0100 |
---|---|---|
committer | Áron Virginás-Tar <aron.virginas-tar@arm.com> | 2019-08-05 12:47:48 +0000 |
commit | 7efb46d283eee8a9cf10f5329176b92b2f830ed6 (patch) | |
tree | 16a99e55dd7b567b8cb5a73add6de963bd4166c0 /NnapiSupport.txt | |
parent | a3047803c4f6b2a3299af2a7b4a0c20a51fe2074 (diff) | |
download | android-nn-driver-7efb46d283eee8a9cf10f5329176b92b2f830ed6.tar.gz |
IVGCVSW-3340 Add support for Quantized_LSTM to HAL1.2 Driver
* Added conversion method to HAL1.2 Policy
Signed-off-by: Ellen Norris-Thompson <ellen.norris-thompson@arm.com>
Change-Id: Ida6734d34931148add2f3464c3283191ea34b712
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 4a494305..6f740970 100644 --- a/NnapiSupport.txt +++ b/NnapiSupport.txt @@ -55,6 +55,7 @@ MINIMUM (FLOAT32,QUANT8_ASYMM) PAD_V2 (FLOAT32,QUANT8_ASYMM) PRELU (FLOAT32,QUANT8_ASYMM) QUANTIZE (FLOAT32,QUANT8_ASYMM) +QUANTIZED_16BIT_LSTM (QUANT8_ASYMM) RESIZE_NEAREST_NEIGHBOR (FLOAT32,QUANT8_ASYMM) SOFTMAX (FLOAT32,QUANT8_ASYMM) TRANSPOSE_CONV_2D (FLOAT32,QUANT8_ASYMM) @@ -74,7 +75,6 @@ The following AndroidNN HAL 1.2 operations are currently not supported: CONCATENATION LSTM -QUANTIZED_16BIT_LSTM 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. |