diff options
| author | Michalis Spyrou <michalis.spyrou@arm.com> | 2017-11-30 14:25:57 +0000 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:42:17 +0000 |
| commit | afa5d817b1d083837cd7ea30d32f845d82620c12 (patch) | |
| tree | 1ca2a27ab7108b7137b96fc1547a8b5ac5d9c8f7 /arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h | |
| parent | 631c41a4e3645a948b0f597caa77e8fa91ca0efc (diff) | |
| download | ComputeLibrary-afa5d817b1d083837cd7ea30d32f845d82620c12.tar.gz | |
COMPMID-617 Add validation methods to Kernels
- NEActivationLayer
- NESoftmax
- NEDirectConvolutionLayer
- NENormalizationLayer
- NEPoolingLayer
Change-Id: Ib279f1c1b7f9247679b0d6593aed7393da8fe87b
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/111335
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h')
| -rw-r--r-- | arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h | 10 |
1 files changed, 7 insertions, 3 deletions
diff --git a/arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h b/arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h index 05eb8d6ddc..10f990e7ef 100644 --- a/arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h +++ b/arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h @@ -64,9 +64,13 @@ public: void configure(const ITensor *input1, const ITensor *input2, ITensor *output, float scale, ConvertPolicy overflow_policy, RoundingPolicy rounding_policy); /** Static function to check if given info will lead to a valid configuration of @ref NEPixelWiseMultiplicationKernel * - * @param[in] input1 An input tensor info. Data types supported: U8/QS8/QS16/S16/F16/F32 - * @param[in] input2 An input tensor info. Data types supported: U8, QS8 (only if @p input1 is QS8), QS16 (only if @p input1 is QS16), S16/F16 (only if @p input1 is F16), F32 (only if @p input1 is F32). - * @param[in] output The output tensor info. Data types supported: U8 (Only if both inputs are U8), QS8 (only if both inputs are QS8), QS16 (only if both inputs are QS16), S16/F16 (only if @p input1 is F16), F32 (only if both inputs are F32). + * @note For @p scale equal to 1/255 only round to nearest even (implemented as round half up) is supported. + * For all other scale values only round to zero (implemented as round towards minus infinity) is supported. + * For QS8/QS16 scale = 1 is the only supported value. + * + * @param[in] input1 An input tensor. Data types supported: U8/QS8/QS16/S16/F16/F32 + * @param[in] input2 An input tensor. Data types supported: U8, QS8 (only if @p input1 is QS8), QS16 (only if @p input1 is QS16), S16/F16 (only if @p input1 is F16), F32 (only if @p input1 is F32). + * @param[in] output The output tensor. Data types supported: U8 (Only if both inputs are U8), QS8 (only if both inputs are QS8), QS16 (only if both inputs are QS16), S16/F16 (only if @p input1 is F16), F32 (only if both inputs are F32). * @param[in] scale Scale to apply after multiplication. * Scale must be positive and its value must be either 1/255 or 1/2^n where n is between 0 and 15. * @param[in] overflow_policy Overflow policy. |