diff options
author | Michele Di Giorgio <michele.digiorgio@arm.com> | 2019-09-10 10:42:27 +0100 |
---|---|---|
committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-09-16 14:43:54 +0000 |
commit | d87a7b297a5bfc2bad3ba78ea97754d7894e82ef (patch) | |
tree | c527ede747d386fe8dd1b39a877ea4e9a19a5fd3 /arm_compute/runtime/CL/functions | |
parent | e874ef9b845424dceeac4211ca9dfec24949f03c (diff) | |
download | ComputeLibrary-d87a7b297a5bfc2bad3ba78ea97754d7894e82ef.tar.gz |
COMPMID-2650: Add support for QASYMM16 in CLQuantizationLayer
Change-Id: I51dda621975f522a65d770304bed0ff0f30d1235
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1902
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'arm_compute/runtime/CL/functions')
-rw-r--r-- | arm_compute/runtime/CL/functions/CLQuantizationLayer.h | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/arm_compute/runtime/CL/functions/CLQuantizationLayer.h b/arm_compute/runtime/CL/functions/CLQuantizationLayer.h index 104f8e2eb2..41a03fdc08 100644 --- a/arm_compute/runtime/CL/functions/CLQuantizationLayer.h +++ b/arm_compute/runtime/CL/functions/CLQuantizationLayer.h @@ -43,13 +43,15 @@ public: /** Set the input and output tensors. * * @param[in] input Source tensor. The dimensions over the third will be interpreted as batches. Data types supported: F16/32. - * @param[out] output Destination tensor with the same dimensions of input. Output data type must be QASYMM8. + * @param[out] output Destination tensor with the same dimensions of input. Data types supported: QASYMM8/QASYMM16. + * + * @note Output auto initialization is not supported by this function */ void configure(const ICLTensor *input, ICLTensor *output); /** Static function to check if given info will lead to a valid configuration of @ref CLQuantizationLayer * * @param[in] input Input tensor info. The dimensions over the third will be interpreted as batches. Data types supported: F16/32. - * @param[in] output Output tensor info. Output data type must be QASYMM8. + * @param[in] output Output tensor info. Data types supported: QASYMM8/QASYMM16. * * @return a status */ |