diff options
| author | Freddie Liardet <frederick.liardet@arm.com> | 2021-04-06 15:59:28 +0100 |
|---|---|---|
| committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2021-04-07 16:46:47 +0000 |
| commit | 9d061b0c2a71f24c7fb00184e9409aaeea37f78d (patch) | |
| tree | 80a487dda022fae84cdf09fa26df16a4186deb9f /arm_compute/runtime/NEON/functions/NEConvolutionLayer.h | |
| parent | 37d65e4fd036529a2c7567f1987235d0b0258ab0 (diff) | |
| download | ComputeLibrary-9d061b0c2a71f24c7fb00184e9409aaeea37f78d.tar.gz | |
Add per channel quantization support for NEDeconvolutionLayer
Add QSYMM8_PER_CHANNEL support on weight input for NEDeconvolutionLayer and reference version.
Resolves: COMPMID-3437
Signed-off-by: Freddie Liardet <frederick.liardet@arm.com>
Change-Id: I7c9a28d4d0fea324ed8e5a24fbd0422e5ede145c
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5364
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/NEON/functions/NEConvolutionLayer.h')
| -rw-r--r-- | arm_compute/runtime/NEON/functions/NEConvolutionLayer.h | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/arm_compute/runtime/NEON/functions/NEConvolutionLayer.h b/arm_compute/runtime/NEON/functions/NEConvolutionLayer.h index d2d41c1e8a..b1e85523c5 100644 --- a/arm_compute/runtime/NEON/functions/NEConvolutionLayer.h +++ b/arm_compute/runtime/NEON/functions/NEConvolutionLayer.h @@ -89,7 +89,7 @@ public: * @param[in] input Source tensor. 3 lower dimensions represent a single input [width, height, IFM], * while every optional dimension from 4 and above represent a batch of inputs. * Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32. - * @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported: Same as @p input. + * @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported: Same as @p input, also could be QSYMM8_PER_CHANNEL if input is QASYMM8/QASYMM8_SIGNED. * @param[in] biases Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. * Data type supported: Should match @p input data type, except for input of QASYMM8/QASYMM8_SIGNED type where biases should be of S32 type. * @param[out] output Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs. @@ -110,7 +110,7 @@ public: * @param[in] input Source tensor. 3 lower dimensions represent a single input [width, height, IFM], * while every optional dimension from 4 and above represent a batch of inputs. * Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32. - * @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported:Same as @p input. + * @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported:Same as @p input, also could be QSYMM8_PER_CHANNEL if input is QASYMM8/QASYMM8_SIGNED. * @param[in] biases Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. * Data type supported: Should match @p input data type, except for input of QASYMM8/QASYMM8_SIGNED type where biases should be of S32 type. * @param[in] output Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs. @@ -134,7 +134,7 @@ public: * @param[in] input Source tensor. 3 lower dimensions represent a single input [width, height, IFM], * while every optional dimension from 4 and above represent a batch of inputs. * Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32. - * @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported:Same as @p input. + * @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported:Same as @p input, also could be QSYMM8_PER_CHANNEL if input is QASYMM8/QASYMM8_SIGNED. * @param[in] output Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs. * Data types supported: Same as @p input. * @param[in] conv_info Contains padding and stride information described in @ref PadStrideInfo. |