From db00668890e1aba956e02fa02e1383b54dfd1435 Mon Sep 17 00:00:00 2001 From: steniu01 Date: Wed, 9 Aug 2017 16:26:22 +0100 Subject: COMPMID-478 Implemnt CL direct convolution 5x5 Change-Id: I4b975aff310cda9964d8c5dcee182d5d5c82741b Reviewed-on: http://mpd-gerrit.cambridge.arm.com/83474 Tested-by: Kaizen Reviewed-by: Gian Marco Iodice --- arm_compute/core/CL/kernels/CLDirectConvolutionLayerKernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arm_compute/core/CL/kernels') diff --git a/arm_compute/core/CL/kernels/CLDirectConvolutionLayerKernel.h b/arm_compute/core/CL/kernels/CLDirectConvolutionLayerKernel.h index aa6ecd6631..e225b64bae 100644 --- a/arm_compute/core/CL/kernels/CLDirectConvolutionLayerKernel.h +++ b/arm_compute/core/CL/kernels/CLDirectConvolutionLayerKernel.h @@ -53,6 +53,7 @@ public: * @note: DirectConvolution only works in the following configurations: * 1x1 convolution with stride_x = 1/2/3, stride_y = 1/2/3 * 3x3 convolution with stride_x = 1/2, stride_y = 1/2 + * 5x5 convolution with stride_x = 1/2, stride_y = 1/2 * * @param[in] input The input tensor to convolve. 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: F16/F32. -- cgit v1.2.1