diff options
| author | Teresa Charlin <teresa.charlinreyes@arm.com> | 2021-04-28 10:58:49 +0100 |
|---|---|---|
| committer | Sheri Zhang <sheri.zhang@arm.com> | 2021-04-30 17:18:15 +0000 |
| commit | 62687420901c12be609426f3cf9dee300d25746a (patch) | |
| tree | d9eaf86763aaef2debb4b3ac8ddd6c7064468325 /arm_compute/runtime/CL/functions/CLWinogradConvolutionLayer.h | |
| parent | 50929ef951880469b9d579323d2f9c9f5025327d (diff) | |
| download | ComputeLibrary-62687420901c12be609426f3cf9dee300d25746a.tar.gz | |
Update operator list documentation. Part 2.
All data type and data layout information for the operators are store in the function header files
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I30b564f7eda6bbd99bf3ad36ddb6639ac118eb8b
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/319829
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
Comments-Addressed: bsgcomp <bsgcomp@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5531
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/runtime/CL/functions/CLWinogradConvolutionLayer.h')
| -rw-r--r-- | arm_compute/runtime/CL/functions/CLWinogradConvolutionLayer.h | 12 |
1 files changed, 11 insertions, 1 deletions
diff --git a/arm_compute/runtime/CL/functions/CLWinogradConvolutionLayer.h b/arm_compute/runtime/CL/functions/CLWinogradConvolutionLayer.h index 9ced69c1bb..7b42932f82 100644 --- a/arm_compute/runtime/CL/functions/CLWinogradConvolutionLayer.h +++ b/arm_compute/runtime/CL/functions/CLWinogradConvolutionLayer.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2018-2020 Arm Limited. + * Copyright (c) 2018-2021 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -62,6 +62,16 @@ public: ~CLWinogradConvolutionLayer(); /** Set the input and output tensors. * + * Valid data layouts: + * - NHWC + * - NCHW + * + * Valid data type configurations: + * |src0 |src1 |src2 |dst | + * |:--------------|:--------------|:------|:--------------| + * |F16 |F16 |F16 |F16 | + * |F32 |F32 |F32 |F32 | + * * @note: This function only works with 3x3,3x1,1x3,5x5,5x1,1x5,7x1 and 1x7 kernels along with unit strides for both NCHW and NHWC data layout * @note Some Winograd configurations (i.e. F(4x4, 5x5)) are supported only with enable_fast_math = true * |