diff options
author | Giorgio Arena <giorgio.arena@arm.com> | 2018-04-25 12:07:29 +0100 |
---|---|---|
committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:52:54 +0000 |
commit | dcb5b284300c34d5984091cfe99559cc420e59bb (patch) | |
tree | 2801819da649371088f47a6210d014e052af3473 /arm_compute | |
parent | 028283c15a6c5d42c0794a733f7e26db84a1730a (diff) | |
download | ComputeLibrary-dcb5b284300c34d5984091cfe99559cc420e59bb.tar.gz |
COMPMID-1048 Add NHWC data format support to Winograd filter transform 4x4_3x3
Change-Id: Ifd125fcb5451dbac3c28b15a9471048a74fee0ad
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/128987
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute')
-rw-r--r-- | arm_compute/core/CL/kernels/CLWinogradFilterTransformKernel.h | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/arm_compute/core/CL/kernels/CLWinogradFilterTransformKernel.h b/arm_compute/core/CL/kernels/CLWinogradFilterTransformKernel.h index 828e2e521a..7360646019 100644 --- a/arm_compute/core/CL/kernels/CLWinogradFilterTransformKernel.h +++ b/arm_compute/core/CL/kernels/CLWinogradFilterTransformKernel.h @@ -51,8 +51,9 @@ public: * @note Winograd filter transform supports the following configurations: * F(output tile, kernel size):F(2x2, 3x3), F(4x4, 3x3), F(4x4, 5x5) * Strides: only unit strides + * Data Layout: NCHW for all configurations, NHWC for F(4x4, 3x3) * - * @param[in] input Source tensor. The input is a 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM] (NCHW data layout). Data types supported: F32. + * @param[in] input Source tensor. The input is a 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM] (NCHW data layout) or [IFM, kernel_x, kernel_y, OFM] (NHWC data layout). Data types supported: F32. * @param[out] output The output tensor. The shape for this tensor can be calculated using the utility function @p compute_winograd_filter_transform_shape. Data types supported: Same as @p input * @param[in] winograd_info Contains Winograd's information described in @ref WinogradInfo */ @@ -62,8 +63,9 @@ public: * @note Winograd filter transform supports the following configurations: * F(output tile, kernel size):F(2x2, 3x3), F(4x4, 3x3), F(4x4, 5x5) * Strides: only unit strides + * Data Layout: NCHW for all configurations, NHWC for F(4x4, 3x3) * - * @param[in] input Source tensor. The input is a 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM] (NCHW data layout). Data types supported: F32. + * @param[in] input Source tensor. The input is a 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM] (NCHW data layout) or [IFM, kernel_x, kernel_y, OFM] (NHWC data layout). Data types supported: F32. * @param[out] output The output tensor. The shape for this tensor can be calculated using the utility function @p compute_winograd_filter_transform_shape. Data types supported: Same as @p input * @param[in] winograd_info Contains Winograd's information described in @ref WinogradInfo * |