diff options
| author | Sadik Armagan <sadik.armagan@arm.com> | 2019-07-30 09:43:18 +0100 |
|---|---|---|
| committer | Sadik Armagan <sadik.armagan@arm.com> | 2019-07-30 08:48:58 +0000 |
| commit | 5a476a88c3295168f5480b5861f59255b29d8433 (patch) | |
| tree | 230393f3ea4135e7a6a880c8fc14714c15e81203 /NnapiSupport.txt | |
| parent | 0a87936e7261fc074797111d274c40fca17d9509 (diff) | |
| download | android-nn-driver-5a476a88c3295168f5480b5861f59255b29d8433.tar.gz | |
IVGCVSW-3592 Add Support for Quantize to HAL 1.2 Driver
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ie7421078b2bdd16d7ac67b635953b34721e8c8fe
Diffstat (limited to 'NnapiSupport.txt')
| -rw-r--r-- | NnapiSupport.txt | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/NnapiSupport.txt b/NnapiSupport.txt index a57768d7..47c5149a 100644 --- a/NnapiSupport.txt +++ b/NnapiSupport.txt @@ -52,7 +52,9 @@ CONV_2D (FLOAT32,QUANT8_ASYMM) DEPTHWISE_CONV_2D (FLOAT32,QUANT8_ASYMM) MAXIMUM (FLOAT32,QUANT8_ASYMM) MINIMUM (FLOAT32,QUANT8_ASYMM) +PAD_V2 (FLOAT32,QUANT8_ASYMM) PRELU (FLOAT32,QUANT8_ASYMM) +QUANTIZE (FLOAT32,QUANT8_ASYMM) RESIZE_NEAREST_NEIGHBOR (FLOAT32,QUANT8_ASYMM) SOFTMAX (FLOAT32,QUANT8_ASYMM) @@ -71,8 +73,6 @@ The following AndroidNN HAL 1.2 operations are currently not supported: CONCATENATION LSTM -PAD_V2 -QUANTIZE QUANTIZED_16BIT_LSTM TRANSPOSE_CONV_2D |