diff options
| author | Georgios Pinitas <georgios.pinitas@arm.com> | 2018-07-16 14:40:09 +0100 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:54:54 +0000 |
| commit | e29acf14f5c3f2d2c20799a1ea3e4aad50dff834 (patch) | |
| tree | ca7a01ed169605404b2b954fc0d174ee00e121f2 /arm_compute/runtime/CL/functions/CLWidthConcatenateLayer.h | |
| parent | 76259ca5a74a60ef2b80f29431ab53bbac9fdb63 (diff) | |
| download | ComputeLibrary-e29acf14f5c3f2d2c20799a1ea3e4aad50dff834.tar.gz | |
COMPMID-1365: Add support for NHWC in CLDepthConcatenateLayer
Change-Id: I3ed55bdb95d888aff0b0b76fb841bf1669659308
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/139963
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Diffstat (limited to 'arm_compute/runtime/CL/functions/CLWidthConcatenateLayer.h')
| -rw-r--r-- | arm_compute/runtime/CL/functions/CLWidthConcatenateLayer.h | 14 |
1 files changed, 10 insertions, 4 deletions
diff --git a/arm_compute/runtime/CL/functions/CLWidthConcatenateLayer.h b/arm_compute/runtime/CL/functions/CLWidthConcatenateLayer.h index 289191e030..44462b02b2 100644 --- a/arm_compute/runtime/CL/functions/CLWidthConcatenateLayer.h +++ b/arm_compute/runtime/CL/functions/CLWidthConcatenateLayer.h @@ -50,14 +50,20 @@ public: CLWidthConcatenateLayer(); /** Initialise the kernel's inputs vector and output. * - * @param[in,out] inputs_vector The vectors containing all the tensors to concatenate. Data types supported: QASYMM8/F16/F32. - * @param[out] output Output tensor. Data types supported: Same as @p input. + * @param[in] inputs_vector The vectors containing all the tensors to concatenate. Data types supported: QASYMM8/F16/F32. + * Dimensions of all the inputs should match apart for the width which can differ. + * @param[out] output Output tensor. Data types supported: Same as @p input. + * Output tensor dimensions are the same with the inputs from the second dimension and above. + * The first dimension (width) is the sum of the input tensors' widths. */ void configure(std::vector<ICLTensor *> inputs_vector, ICLTensor *output); /** Static function to check if given info will lead to a valid configuration of @ref CLDepthConcatenateLayerKernel * - * @param[in] inputs_vector The vectors containing all the tensors info to concatenate. Data types supported: QASYMM8/F16/F32. - * @param[in] output Output tensor info. Data types supported: Same as @p input. + * @param[in] inputs_vector The vectors containing all the tensors to concatenate. Data types supported: QASYMM8/F16/F32. + * Dimensions of all the inputs should match apart for the width which can differ. + * @param[in] output Output tensor. Data types supported: Same as @p input. + * Output tensor dimensions are the same with the inputs from the second dimension and above. + * The first dimension (width) is the sum of the input tensors' widths. * * @return a status */ |